Training in progress, step 12822

README.md

@@ -0,0 +1,53 @@
+---
+license: mit
+base_model: Josephgflowers/TinyLlama-Cinder-Math-Train
+tags:
+- generated_from_trainer
+model-index:
+- name: TinyLlama-Cinder-Tiny-Agent
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# TinyLlama-Cinder-Tiny-Agent
+
+This model is a fine-tuned version of [Josephgflowers/TinyLlama-Cinder-Math-Train](https://huggingface.co/Josephgflowers/TinyLlama-Cinder-Math-Train) on an unknown dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 12
+- eval_batch_size: 32
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 1.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.41.0.dev0
+- Pytorch 2.2.2+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.0,
+    "total_flos": 8.2628573134848e+17,
+    "train_loss": 0.7277259675255335,
+    "train_runtime": 75113.2183,
+    "train_samples": 65000,
+    "train_samples_per_second": 0.865,
+    "train_steps_per_second": 0.072
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "Josephgflowers/TinyLlama-Cinder-Tiny-Agent",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5632,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 22,
+  "num_key_value_heads": 4,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.0.dev0",
+  "use_cache": false,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "max_length": 2048,
+  "pad_token_id": 0,
+  "transformers_version": "4.41.0.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c86cd1858d9891e7cd52ccb63a868d208a7a0731b84df044c8506a2f0a7e1fb
+size 4400216536

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,41 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.0,
+    "total_flos": 8.2628573134848e+17,
+    "train_loss": 0.7277259675255335,
+    "train_runtime": 75113.2183,
+    "train_samples": 65000,
+    "train_samples_per_second": 0.865,
+    "train_steps_per_second": 0.072
+}

trainer_state.json

@@ -0,0 +1,420 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 5417,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.018460402436773122,
+      "grad_norm": 72293.6015625,
+      "learning_rate": 4.907697987816135e-05,
+      "loss": 0.7984,
+      "step": 100
+    },
+    {
+      "epoch": 0.036920804873546244,
+      "grad_norm": 86618.71875,
+      "learning_rate": 4.815395975632269e-05,
+      "loss": 0.7874,
+      "step": 200
+    },
+    {
+      "epoch": 0.05538120731031936,
+      "grad_norm": 82291.1953125,
+      "learning_rate": 4.723093963448403e-05,
+      "loss": 0.7683,
+      "step": 300
+    },
+    {
+      "epoch": 0.07384160974709249,
+      "grad_norm": 72406.7265625,
+      "learning_rate": 4.6307919512645376e-05,
+      "loss": 0.7721,
+      "step": 400
+    },
+    {
+      "epoch": 0.0923020121838656,
+      "grad_norm": 82859.0,
+      "learning_rate": 4.538489939080672e-05,
+      "loss": 0.7672,
+      "step": 500
+    },
+    {
+      "epoch": 0.11076241462063872,
+      "grad_norm": 72674.453125,
+      "learning_rate": 4.4461879268968066e-05,
+      "loss": 0.7741,
+      "step": 600
+    },
+    {
+      "epoch": 0.12922281705741184,
+      "grad_norm": 74598.8828125,
+      "learning_rate": 4.3538859147129405e-05,
+      "loss": 0.7684,
+      "step": 700
+    },
+    {
+      "epoch": 0.14768321949418498,
+      "grad_norm": 75325.09375,
+      "learning_rate": 4.261583902529076e-05,
+      "loss": 0.7706,
+      "step": 800
+    },
+    {
+      "epoch": 0.1661436219309581,
+      "grad_norm": 80050.4921875,
+      "learning_rate": 4.1692818903452095e-05,
+      "loss": 0.771,
+      "step": 900
+    },
+    {
+      "epoch": 0.1846040243677312,
+      "grad_norm": 71205.3359375,
+      "learning_rate": 4.076979878161344e-05,
+      "loss": 0.7458,
+      "step": 1000
+    },
+    {
+      "epoch": 0.20306442680450434,
+      "grad_norm": 71098.4765625,
+      "learning_rate": 3.9846778659774785e-05,
+      "loss": 0.7632,
+      "step": 1100
+    },
+    {
+      "epoch": 0.22152482924127745,
+      "grad_norm": 79350.5859375,
+      "learning_rate": 3.892375853793613e-05,
+      "loss": 0.7715,
+      "step": 1200
+    },
+    {
+      "epoch": 0.23998523167805058,
+      "grad_norm": 78053.2578125,
+      "learning_rate": 3.800073841609747e-05,
+      "loss": 0.7582,
+      "step": 1300
+    },
+    {
+      "epoch": 0.2584456341148237,
+      "grad_norm": 72609.0078125,
+      "learning_rate": 3.707771829425882e-05,
+      "loss": 0.7547,
+      "step": 1400
+    },
+    {
+      "epoch": 0.27690603655159685,
+      "grad_norm": 75624.9453125,
+      "learning_rate": 3.615469817242016e-05,
+      "loss": 0.7432,
+      "step": 1500
+    },
+    {
+      "epoch": 0.29536643898836995,
+      "grad_norm": 67118.828125,
+      "learning_rate": 3.5231678050581504e-05,
+      "loss": 0.7522,
+      "step": 1600
+    },
+    {
+      "epoch": 0.31382684142514305,
+      "grad_norm": 77685.6171875,
+      "learning_rate": 3.430865792874285e-05,
+      "loss": 0.7529,
+      "step": 1700
+    },
+    {
+      "epoch": 0.3322872438619162,
+      "grad_norm": 80151.4609375,
+      "learning_rate": 3.338563780690419e-05,
+      "loss": 0.7558,
+      "step": 1800
+    },
+    {
+      "epoch": 0.3507476462986893,
+      "grad_norm": 68374.609375,
+      "learning_rate": 3.246261768506554e-05,
+      "loss": 0.7547,
+      "step": 1900
+    },
+    {
+      "epoch": 0.3692080487354624,
+      "grad_norm": 69225.65625,
+      "learning_rate": 3.153959756322688e-05,
+      "loss": 0.7283,
+      "step": 2000
+    },
+    {
+      "epoch": 0.38766845117223553,
+      "grad_norm": 93264.3984375,
+      "learning_rate": 3.061657744138822e-05,
+      "loss": 0.7368,
+      "step": 2100
+    },
+    {
+      "epoch": 0.4061288536090087,
+      "grad_norm": 81487.3125,
+      "learning_rate": 2.9693557319549568e-05,
+      "loss": 0.7531,
+      "step": 2200
+    },
+    {
+      "epoch": 0.4245892560457818,
+      "grad_norm": 72823.8125,
+      "learning_rate": 2.8770537197710913e-05,
+      "loss": 0.7216,
+      "step": 2300
+    },
+    {
+      "epoch": 0.4430496584825549,
+      "grad_norm": 73118.8203125,
+      "learning_rate": 2.7847517075872255e-05,
+      "loss": 0.7356,
+      "step": 2400
+    },
+    {
+      "epoch": 0.46151006091932806,
+      "grad_norm": 68678.484375,
+      "learning_rate": 2.69244969540336e-05,
+      "loss": 0.7308,
+      "step": 2500
+    },
+    {
+      "epoch": 0.47997046335610116,
+      "grad_norm": 73918.640625,
+      "learning_rate": 2.6001476832194942e-05,
+      "loss": 0.7235,
+      "step": 2600
+    },
+    {
+      "epoch": 0.49843086579287427,
+      "grad_norm": 66172.796875,
+      "learning_rate": 2.5078456710356284e-05,
+      "loss": 0.7283,
+      "step": 2700
+    },
+    {
+      "epoch": 0.5168912682296474,
+      "grad_norm": 66544.1015625,
+      "learning_rate": 2.415543658851763e-05,
+      "loss": 0.7228,
+      "step": 2800
+    },
+    {
+      "epoch": 0.5353516706664205,
+      "grad_norm": 66939.625,
+      "learning_rate": 2.3232416466678974e-05,
+      "loss": 0.7095,
+      "step": 2900
+    },
+    {
+      "epoch": 0.5538120731031937,
+      "grad_norm": 67865.15625,
+      "learning_rate": 2.230939634484032e-05,
+      "loss": 0.7248,
+      "step": 3000
+    },
+    {
+      "epoch": 0.5722724755399667,
+      "grad_norm": 63117.76953125,
+      "learning_rate": 2.138637622300166e-05,
+      "loss": 0.7147,
+      "step": 3100
+    },
+    {
+      "epoch": 0.5907328779767399,
+      "grad_norm": 59398.1796875,
+      "learning_rate": 2.0463356101163006e-05,
+      "loss": 0.7031,
+      "step": 3200
+    },
+    {
+      "epoch": 0.6091932804135131,
+      "grad_norm": 63816.08203125,
+      "learning_rate": 1.954033597932435e-05,
+      "loss": 0.7144,
+      "step": 3300
+    },
+    {
+      "epoch": 0.6276536828502861,
+      "grad_norm": 70370.5625,
+      "learning_rate": 1.8617315857485696e-05,
+      "loss": 0.7141,
+      "step": 3400
+    },
+    {
+      "epoch": 0.6461140852870593,
+      "grad_norm": 63610.734375,
+      "learning_rate": 1.7694295735647038e-05,
+      "loss": 0.694,
+      "step": 3500
+    },
+    {
+      "epoch": 0.6645744877238324,
+      "grad_norm": 59664.05078125,
+      "learning_rate": 1.6771275613808383e-05,
+      "loss": 0.7086,
+      "step": 3600
+    },
+    {
+      "epoch": 0.6830348901606055,
+      "grad_norm": 64207.88671875,
+      "learning_rate": 1.5848255491969728e-05,
+      "loss": 0.7138,
+      "step": 3700
+    },
+    {
+      "epoch": 0.7014952925973786,
+      "grad_norm": 79748.2734375,
+      "learning_rate": 1.4925235370131068e-05,
+      "loss": 0.6985,
+      "step": 3800
+    },
+    {
+      "epoch": 0.7199556950341518,
+      "grad_norm": 72216.671875,
+      "learning_rate": 1.4002215248292413e-05,
+      "loss": 0.7019,
+      "step": 3900
+    },
+    {
+      "epoch": 0.7384160974709248,
+      "grad_norm": 74815.6328125,
+      "learning_rate": 1.3079195126453758e-05,
+      "loss": 0.687,
+      "step": 4000
+    },
+    {
+      "epoch": 0.756876499907698,
+      "grad_norm": 61482.41796875,
+      "learning_rate": 1.2156175004615102e-05,
+      "loss": 0.6983,
+      "step": 4100
+    },
+    {
+      "epoch": 0.7753369023444711,
+      "grad_norm": 73800.75,
+      "learning_rate": 1.1233154882776445e-05,
+      "loss": 0.7004,
+      "step": 4200
+    },
+    {
+      "epoch": 0.7937973047812442,
+      "grad_norm": 75985.421875,
+      "learning_rate": 1.0310134760937789e-05,
+      "loss": 0.7097,
+      "step": 4300
+    },
+    {
+      "epoch": 0.8122577072180174,
+      "grad_norm": 67175.03125,
+      "learning_rate": 9.387114639099132e-06,
+      "loss": 0.6781,
+      "step": 4400
+    },
+    {
+      "epoch": 0.8307181096547904,
+      "grad_norm": 68520.875,
+      "learning_rate": 8.464094517260476e-06,
+      "loss": 0.6857,
+      "step": 4500
+    },
+    {
+      "epoch": 0.8491785120915636,
+      "grad_norm": 65612.703125,
+      "learning_rate": 7.541074395421821e-06,
+      "loss": 0.6971,
+      "step": 4600
+    },
+    {
+      "epoch": 0.8676389145283367,
+      "grad_norm": 63280.83203125,
+      "learning_rate": 6.618054273583164e-06,
+      "loss": 0.6942,
+      "step": 4700
+    },
+    {
+      "epoch": 0.8860993169651098,
+      "grad_norm": 68478.2890625,
+      "learning_rate": 5.6950341517445085e-06,
+      "loss": 0.7028,
+      "step": 4800
+    },
+    {
+      "epoch": 0.904559719401883,
+      "grad_norm": 68026.8125,
+      "learning_rate": 4.772014029905853e-06,
+      "loss": 0.6694,
+      "step": 4900
+    },
+    {
+      "epoch": 0.9230201218386561,
+      "grad_norm": 64797.25390625,
+      "learning_rate": 3.848993908067195e-06,
+      "loss": 0.704,
+      "step": 5000
+    },
+    {
+      "epoch": 0.9414805242754292,
+      "grad_norm": 71872.890625,
+      "learning_rate": 2.9259737862285397e-06,
+      "loss": 0.6946,
+      "step": 5100
+    },
+    {
+      "epoch": 0.9599409267122023,
+      "grad_norm": 74217.3125,
+      "learning_rate": 2.002953664389884e-06,
+      "loss": 0.6796,
+      "step": 5200
+    },
+    {
+      "epoch": 0.9784013291489755,
+      "grad_norm": 68286.15625,
+      "learning_rate": 1.0799335425512278e-06,
+      "loss": 0.6966,
+      "step": 5300
+    },
+    {
+      "epoch": 0.9968617315857485,
+      "grad_norm": 137991.28125,
+      "learning_rate": 1.5691342071257153e-07,
+      "loss": 0.7014,
+      "step": 5400
+    },
+    {
+      "epoch": 1.0,
+      "step": 5417,
+      "total_flos": 8.2628573134848e+17,
+      "train_loss": 0.7277259675255335,
+      "train_runtime": 75113.2183,
+      "train_samples_per_second": 0.865,
+      "train_steps_per_second": 0.072
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 5417,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 5417,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 8.2628573134848e+17,
+  "train_batch_size": 12,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c44c38eb09a6b2599756766edbc167c8760d5ab86cbaedecff96098292537cf
+size 5112