Training in progress, epoch 0

README.md

@@ -4,6 +4,7 @@ license: llama3
 base_model: meta-llama/Meta-Llama-3-8B
 tags:
 - llama-factory
+- full
 - generated_from_trainer
 model-index:
 - name: llama3_8b_baseline_instructskillmix
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # llama3_8b_baseline_instructskillmix
 
-This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on an unknown dataset.
+This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the PrincetonPLI/Instruct-SkillMix-SDD dataset.
 It achieves the following results on the evaluation set:
 - Loss: nan
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 1.6,
+    "eval_loss": NaN,
+    "eval_runtime": 1.8533,
+    "eval_samples_per_second": 54.497,
+    "eval_steps_per_second": 2.158,
+    "total_flos": 2.833014287331492e+17,
+    "train_loss": 2741718698.6666665,
+    "train_runtime": 750.1141,
+    "train_samples_per_second": 7.675,
+    "train_steps_per_second": 0.004
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.6,
+    "eval_loss": NaN,
+    "eval_runtime": 1.8533,
+    "eval_samples_per_second": 54.497,
+    "eval_steps_per_second": 2.158
+}

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fe539379e2d7db955eeb676cd8d9f54e2e235f030bf3e11e1e28087bf9a2d87
+oid sha256:01e75985d500ca5708e9c816a9372bd2d7431aab5de48e3fe37de82e9510476f
 size 4976698672

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6464d95d51be7644f72596bcb8be974b9763735a7b9f9716f6fc23a9cbb258a6
+oid sha256:e625340fe242c252b27e704612ba89ce4c9c0b19b5fd94df215b6b347a3025f7
 size 4999802720

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2411be315fd7e1c238c0c358255a9ca8cb559ac7c9f9df7d3145fc0374654aa2
+oid sha256:1b7edca4ff8f0162d7e025ad5605a3f5510b97a233d5eb729ea8dacf0dbc4883
 size 4915916176

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ea974b209c1000324a60d7522f76fad8acd259f36bb4d3acf7b044acf4b1b0b
+oid sha256:adac09dfd106ee8a58808585783d79232e9535807e30fef86632634f3ebc9d5e
 size 1168138808

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.6,
+    "total_flos": 2.833014287331492e+17,
+    "train_loss": 2741718698.6666665,
+    "train_runtime": 750.1141,
+    "train_samples_per_second": 7.675,
+    "train_steps_per_second": 0.004
+}

trainer_log.jsonl

@@ -1,3 +1,3 @@
-{"current_steps": 1, "total_steps": 3, "eval_loss": NaN, "epoch": 0.5333333333333333, "percentage": 33.33, "elapsed_time": "0:01:48", "remaining_time": "0:03:37"}
-{"current_steps": 3, "total_steps": 3, "eval_loss": NaN, "epoch": 1.6, "percentage": 100.0, "elapsed_time": "0:09:27", "remaining_time": "0:00:00"}
-{"current_steps": 3, "total_steps": 3, "epoch": 1.6, "percentage": 100.0, "elapsed_time": "0:12:28", "remaining_time": "0:00:00"}
+{"current_steps": 1, "total_steps": 3, "eval_loss": 1.8345630168914795, "epoch": 0.5333333333333333, "percentage": 33.33, "elapsed_time": "0:01:37", "remaining_time": "0:03:15"}
+{"current_steps": 3, "total_steps": 3, "eval_loss": 1.7066795825958252, "epoch": 1.6, "percentage": 100.0, "elapsed_time": "0:07:02", "remaining_time": "0:00:00"}
+{"current_steps": 3, "total_steps": 3, "epoch": 1.6, "percentage": 100.0, "elapsed_time": "0:08:56", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,58 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.6,
+  "eval_steps": 500,
+  "global_step": 3,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5333333333333333,
+      "eval_loss": NaN,
+      "eval_runtime": 1.6602,
+      "eval_samples_per_second": 60.835,
+      "eval_steps_per_second": 2.409,
+      "step": 1
+    },
+    {
+      "epoch": 1.6,
+      "eval_loss": NaN,
+      "eval_runtime": 2.5765,
+      "eval_samples_per_second": 39.201,
+      "eval_steps_per_second": 1.552,
+      "step": 3
+    },
+    {
+      "epoch": 1.6,
+      "step": 3,
+      "total_flos": 2.833014287331492e+17,
+      "train_loss": 2741718698.6666665,
+      "train_runtime": 750.1141,
+      "train_samples_per_second": 7.675,
+      "train_steps_per_second": 0.004
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 3,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 2.833014287331492e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a26eb37e59e7b778758ab61d53eeed1ddc1ece19b7851fd851744b0fb9ab9ae0
-size 6904
+oid sha256:343eb747b35decccf2f0d14a33e9de26b6ddff299f2fb998ea4272af8f5c8bf6
+size 7160