Training in progress, step 50

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:216c5222dbcb5ff5f52be7e8f46a9e2b8eafc2fcae66f4d5dcf5f48ec85747f8
+oid sha256:1da099a0d87099a0b0c9bbf7ea0ae5a6eabcb8d3810f4e9df2b957493c6c6cd5
 size 441154988

runs/Jun15_00-36-15_92b2e0e6fb20/events.out.tfevents.1749947776.92b2e0e6fb20.2194.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68675bc2ed356d6254de5ab1384465e36b4be95c84b4e8a3d42ed7285f48064e
+size 4184

runs/Jun15_00-36-38_92b2e0e6fb20/events.out.tfevents.1749947799.92b2e0e6fb20.2194.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b53fa14b07f1f332f117f6e642eab76308f876681d29b0a1619b45f1a1bf7b14
+size 7232

trainer_state.json

@@ -0,0 +1,81 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 250,
+  "global_step": 50,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0,
+      "step": 0,
+      "train/classification_loss": 0.6716318130493164,
+      "train/contrastive_loss": 6.973960876464844,
+      "train/negative_loss": 6.973352909088135,
+      "train/num_negatives": 190,
+      "train/num_positives": 50,
+      "train/positive_loss": 0.0006079699960537255,
+      "train/total_loss": 2.0664238929748535
+    },
+    {
+      "epoch": 0,
+      "step": 0,
+      "train/classification_loss": 0.6844258904457092,
+      "train/contrastive_loss": 6.779294490814209,
+      "train/negative_loss": 6.7774882316589355,
+      "train/num_negatives": 192,
+      "train/num_positives": 48,
+      "train/positive_loss": 0.0018063625320792198,
+      "train/total_loss": 2.0402848720550537
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 5.838413238525391,
+      "learning_rate": 9.800000000000001e-06,
+      "loss": 1.4132,
+      "step": 50
+    },
+    {
+      "epoch": 5.0,
+      "step": 50,
+      "total_flos": 0.0,
+      "train_loss": 1.413243408203125,
+      "train_runtime": 29.4518,
+      "train_samples_per_second": 53.647,
+      "train_steps_per_second": 1.698
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 50,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "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 sha256:1cf55407d703d9184ef351e313b0bda1b55c3a6bf45440f6046ba6213b87acd0
+oid sha256:6ca0afef15a0edecfaa88b54e14baf2e856c7793f28bd79fd10178152b6b37f8
 size 5368