Model save

README.md

@@ -16,6 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
 # checkpoints
 
 This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.6953
 
 ## Model description
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 0.13043478260869565,
+    "eval_loss": 1.6952797174453735,
+    "eval_runtime": 2.2512,
+    "eval_samples_per_second": 274.076,
+    "eval_steps_per_second": 4.442,
+    "total_flos": 3.355230384370483e+16,
+    "train_loss": 1.4136702219645183,
+    "train_runtime": 204.3723,
+    "train_samples_per_second": 7.516,
+    "train_steps_per_second": 0.015
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 0.13043478260869565,
+    "eval_loss": 1.6952797174453735,
+    "eval_runtime": 2.2512,
+    "eval_samples_per_second": 274.076,
+    "eval_steps_per_second": 4.442
+}

model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ee6b0483c655c8f927d85233354ec5564188ee19f414da0ec1b0636888e345a
+oid sha256:370eaa5179722f54e74f081398b3a7d40e1233daee98192d4ec14b278a8c0f76
 size 4943162336

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d63400f39bfaa3b510c6d6d01336ce8ee448d93ae03ed5c27bfadf7085d146c
+oid sha256:4d432155046b2c474b4e47bb4876fb47d214736dc45fb388cd803b026cbbcb06
 size 4999819336

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04b95ab745ac9310c4ee740598a5c987c13d70ad061d019e5515001e01f01c6a
+oid sha256:f593d9685e3919788f1bbdb9c787e48f9ae37c349ed10796b146267a2d55e906
 size 4540516344

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.13043478260869565,
+    "total_flos": 3.355230384370483e+16,
+    "train_loss": 1.4136702219645183,
+    "train_runtime": 204.3723,
+    "train_samples_per_second": 7.516,
+    "train_steps_per_second": 0.015
+}

trainer_state.json

@@ -0,0 +1,50 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.13043478260869565,
+  "eval_steps": 500,
+  "global_step": 3,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.13043478260869565,
+      "eval_loss": 1.6952797174453735,
+      "eval_runtime": 1.8822,
+      "eval_samples_per_second": 327.804,
+      "eval_steps_per_second": 5.313,
+      "step": 3
+    },
+    {
+      "epoch": 0.13043478260869565,
+      "step": 3,
+      "total_flos": 3.355230384370483e+16,
+      "train_loss": 1.4136702219645183,
+      "train_runtime": 204.3723,
+      "train_samples_per_second": 7.516,
+      "train_steps_per_second": 0.015
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 3,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.355230384370483e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b004b8ecc53af2f5aa6018afbdcfb055134bdd973aa4067e4e5f1da512ed7679
+oid sha256:441bf1d619e881a2104e88d655daeeb8872b3ba8a79f41c69e024e0d02716a9e
 size 6520