model files

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "google/gemma-2b-it",
+  "architectures": [
+    "GemmaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "head_dim": 256,
+  "hidden_act": "gelu",
+  "hidden_activation": null,
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 16384,
+  "max_position_embeddings": 8192,
+  "model_type": "gemma",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 18,
+  "num_key_value_heads": 1,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.2",
+  "use_cache": true,
+  "vocab_size": 256000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.39.2"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9ac2d799b68b1018159b7f7c2655128311fa61e1324cf2d79656f65ee60af23
+size 4911635192

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:779b7cc0def1589539509194e57f09f47b7ad49f04298e25b14536dc54de8703
+size 4978830584

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ccc33f8ecaadfc62ec331af15966a867104d99fbd8efa7698d31d56b520e7e7
+size 134242760

model.safetensors.index.json

@@ -0,0 +1,171 @@
+{
+  "metadata": {
+    "total_size": 10024689664
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.norm.weight": "model-00003-of-00003.safetensors"
+  }
+}

trainer_state.json

@@ -0,0 +1,330 @@
+{
+  "best_metric": 2.5675697326660156,
+  "best_model_checkpoint": "/uoa/scratch/users/u04ob20/attrib/data/models/google-gemma-2b-it/checkpoint-1302",
+  "epoch": 10.0,
+  "eval_steps": 651,
+  "global_step": 13020,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5,
+      "grad_norm": 12.144696235656738,
+      "learning_rate": 4.75e-05,
+      "loss": 2.613,
+      "step": 651
+    },
+    {
+      "epoch": 0.5,
+      "eval_loss": 2.6113576889038086,
+      "eval_runtime": 21.157,
+      "eval_samples_per_second": 14.889,
+      "eval_steps_per_second": 0.945,
+      "step": 651
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 7.70678186416626,
+      "learning_rate": 4.5e-05,
+      "loss": 2.4795,
+      "step": 1302
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 2.5675697326660156,
+      "eval_runtime": 21.2452,
+      "eval_samples_per_second": 14.827,
+      "eval_steps_per_second": 0.941,
+      "step": 1302
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 5.883556365966797,
+      "learning_rate": 4.25e-05,
+      "loss": 2.0065,
+      "step": 1953
+    },
+    {
+      "epoch": 1.5,
+      "eval_loss": 2.6822469234466553,
+      "eval_runtime": 21.2863,
+      "eval_samples_per_second": 14.798,
+      "eval_steps_per_second": 0.94,
+      "step": 1953
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 6.931114673614502,
+      "learning_rate": 4e-05,
+      "loss": 2.0626,
+      "step": 2604
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 2.6481916904449463,
+      "eval_runtime": 21.2145,
+      "eval_samples_per_second": 14.848,
+      "eval_steps_per_second": 0.943,
+      "step": 2604
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 8.269980430603027,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 1.3114,
+      "step": 3255
+    },
+    {
+      "epoch": 2.5,
+      "eval_loss": 3.098555326461792,
+      "eval_runtime": 21.206,
+      "eval_samples_per_second": 14.854,
+      "eval_steps_per_second": 0.943,
+      "step": 3255
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 6.02169942855835,
+      "learning_rate": 3.5e-05,
+      "loss": 1.3535,
+      "step": 3906
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 3.0724563598632812,
+      "eval_runtime": 21.1632,
+      "eval_samples_per_second": 14.884,
+      "eval_steps_per_second": 0.945,
+      "step": 3906
+    },
+    {
+      "epoch": 3.5,
+      "grad_norm": 5.019479751586914,
+      "learning_rate": 3.2500000000000004e-05,
+      "loss": 0.6193,
+      "step": 4557
+    },
+    {
+      "epoch": 3.5,
+      "eval_loss": 3.874941825866699,
+      "eval_runtime": 21.2328,
+      "eval_samples_per_second": 14.836,
+      "eval_steps_per_second": 0.942,
+      "step": 4557
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 7.199153423309326,
+      "learning_rate": 3e-05,
+      "loss": 0.6486,
+      "step": 5208
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 3.907243251800537,
+      "eval_runtime": 21.1438,
+      "eval_samples_per_second": 14.898,
+      "eval_steps_per_second": 0.946,
+      "step": 5208
+    },
+    {
+      "epoch": 4.5,
+      "grad_norm": 3.779839038848877,
+      "learning_rate": 2.7500000000000004e-05,
+      "loss": 0.2773,
+      "step": 5859
+    },
+    {
+      "epoch": 4.5,
+      "eval_loss": 4.521030902862549,
+      "eval_runtime": 21.2882,
+      "eval_samples_per_second": 14.797,
+      "eval_steps_per_second": 0.939,
+      "step": 5859
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 4.8741068840026855,
+      "learning_rate": 2.5e-05,
+      "loss": 0.2937,
+      "step": 6510
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 4.571855545043945,
+      "eval_runtime": 21.1084,
+      "eval_samples_per_second": 14.923,
+      "eval_steps_per_second": 0.947,
+      "step": 6510
+    },
+    {
+      "epoch": 5.5,
+      "grad_norm": 3.5535199642181396,
+      "learning_rate": 2.25e-05,
+      "loss": 0.1624,
+      "step": 7161
+    },
+    {
+      "epoch": 5.5,
+      "eval_loss": 4.86809778213501,
+      "eval_runtime": 21.2022,
+      "eval_samples_per_second": 14.857,
+      "eval_steps_per_second": 0.943,
+      "step": 7161
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 3.6518630981445312,
+      "learning_rate": 2e-05,
+      "loss": 0.1661,
+      "step": 7812
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 4.905501842498779,
+      "eval_runtime": 21.2593,
+      "eval_samples_per_second": 14.817,
+      "eval_steps_per_second": 0.941,
+      "step": 7812
+    },
+    {
+      "epoch": 6.5,
+      "grad_norm": 2.776365041732788,
+      "learning_rate": 1.75e-05,
+      "loss": 0.1053,
+      "step": 8463
+    },
+    {
+      "epoch": 6.5,
+      "eval_loss": 5.140992164611816,
+      "eval_runtime": 21.1963,
+      "eval_samples_per_second": 14.861,
+      "eval_steps_per_second": 0.944,
+      "step": 8463
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 2.7088475227355957,
+      "learning_rate": 1.5e-05,
+      "loss": 0.1071,
+      "step": 9114
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 5.170236110687256,
+      "eval_runtime": 21.1845,
+      "eval_samples_per_second": 14.869,
+      "eval_steps_per_second": 0.944,
+      "step": 9114
+    },
+    {
+      "epoch": 7.5,
+      "grad_norm": 1.5728803873062134,
+      "learning_rate": 1.25e-05,
+      "loss": 0.0749,
+      "step": 9765
+    },
+    {
+      "epoch": 7.5,
+      "eval_loss": 5.332049369812012,
+      "eval_runtime": 21.2173,
+      "eval_samples_per_second": 14.846,
+      "eval_steps_per_second": 0.943,
+      "step": 9765
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 1.9317859411239624,
+      "learning_rate": 1e-05,
+      "loss": 0.0759,
+      "step": 10416
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 5.3781609535217285,
+      "eval_runtime": 21.1066,
+      "eval_samples_per_second": 14.924,
+      "eval_steps_per_second": 0.948,
+      "step": 10416
+    },
+    {
+      "epoch": 8.5,
+      "grad_norm": 1.000594139099121,
+      "learning_rate": 7.5e-06,
+      "loss": 0.0572,
+      "step": 11067
+    },
+    {
+      "epoch": 8.5,
+      "eval_loss": 5.493535041809082,
+      "eval_runtime": 21.2738,
+      "eval_samples_per_second": 14.807,
+      "eval_steps_per_second": 0.94,
+      "step": 11067
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 1.515676498413086,
+      "learning_rate": 5e-06,
+      "loss": 0.059,
+      "step": 11718
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 5.541296005249023,
+      "eval_runtime": 21.1624,
+      "eval_samples_per_second": 14.885,
+      "eval_steps_per_second": 0.945,
+      "step": 11718
+    },
+    {
+      "epoch": 9.5,
+      "grad_norm": 0.9690418243408203,
+      "learning_rate": 2.5e-06,
+      "loss": 0.0466,
+      "step": 12369
+    },
+    {
+      "epoch": 9.5,
+      "eval_loss": 5.654240131378174,
+      "eval_runtime": 21.1813,
+      "eval_samples_per_second": 14.872,
+      "eval_steps_per_second": 0.944,
+      "step": 12369
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.718197762966156,
+      "learning_rate": 0.0,
+      "loss": 0.0474,
+      "step": 13020
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 5.656643390655518,
+      "eval_runtime": 21.2015,
+      "eval_samples_per_second": 14.857,
+      "eval_steps_per_second": 0.943,
+      "step": 13020
+    },
+    {
+      "epoch": 10.0,
+      "step": 13020,
+      "total_flos": 2.7741561881100288e+17,
+      "train_loss": 0.7283723941047071,
+      "train_runtime": 32176.7613,
+      "train_samples_per_second": 5.664,
+      "train_steps_per_second": 0.405
+    }
+  ],
+  "logging_steps": 651,
+  "max_steps": 13020,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 651,
+  "total_flos": 2.7741561881100288e+17,
+  "train_batch_size": 14,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7ea7db924a891dab8a05e67c6c15139ab02e8d8e2079f27e7342cf8878db67c
+size 4475