Training in progress, step 15, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:593171bdc90ce208d1fd8cdc9b93e5460cfb96259ee06fe88cc24bd22e2fc76f
+oid sha256:73911326e456203d756947faff0cd28637f8c4407f111f1beffb103de23b8723
 size 6804608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf2849f55a3470590db89f50f599b38412f1c1a80260d0237c07b5a236c53df7
+oid sha256:2fd9a3692c39d4995c775f1ccede45a0e5ee6163a4b3be2fa4185e66cf56cf61
 size 3633466

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6011dbc1beaf916a24aa0692a7ad3787fe62f4d3127d9859b27643438838594d
+oid sha256:ff5440c0314dadc3defe4b4803f353543d71edfcba882e67961bec9458fb6240
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
+oid sha256:ff2736979009751c0c6b0ddcc5f6544d6f723aa752b4798eab0b70fb76cf0083
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.01710681064898963,
+  "epoch": 0.025660215973484442,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 15,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 246.751,
       "eval_steps_per_second": 123.501,
       "step": 10
+    },
+    {
+      "epoch": 0.018817491713888593,
+      "grad_norm": 0.4462915062904358,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 3.4584,
+      "step": 11
+    },
+    {
+      "epoch": 0.020528172778787556,
+      "grad_norm": 0.48912936449050903,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 3.4649,
+      "step": 12
+    },
+    {
+      "epoch": 0.02223885384368652,
+      "grad_norm": 0.5210543870925903,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 3.4684,
+      "step": 13
+    },
+    {
+      "epoch": 0.02394953490858548,
+      "grad_norm": 0.4840293228626251,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 3.4167,
+      "step": 14
+    },
+    {
+      "epoch": 0.025660215973484442,
+      "grad_norm": 0.4712510406970978,
+      "learning_rate": 5e-05,
+      "loss": 3.3471,
+      "step": 15
+    },
+    {
+      "epoch": 0.025660215973484442,
+      "eval_loss": 3.337122678756714,
+      "eval_runtime": 3.8738,
+      "eval_samples_per_second": 254.275,
+      "eval_steps_per_second": 127.267,
+      "step": 15
     }
   ],
   "logging_steps": 1,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 137170601902080.0,
+  "total_flos": 205755902853120.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null