Training in progress, step 15, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79471e688252e3a48b366caf5b00da4c8287cbbc12ce134bc37532e28b8fb07f
+oid sha256:336cb35b966e8cec27393a90ddd65a6d826c12f8dc5d1c0a4dff81a6b4cf7e2d
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef8b83afe9bd63c19febea689fd6ed6c0d341aafdbc84c30e5fe2cd13b5a8d46
+oid sha256:8993852180f8983a138370358c8456e6a038fd575285422e42056100df118ef2
 size 160284754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c42d4a99df91dcb2725bdd7effbeb06036832b0ca054c032cc94b28425ecaec4
+oid sha256:108c66bcb2b4371a6c18753d50706a380a3d762b454bf590741e9458fde82541
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06829946ff807c7143728448cc1bf384944e638865601317db4b29a92003bb11
+oid sha256:008d83c4f5ee0c3b0aa2ca88e92cb7f21d43acfd48a8bc37442b67fb3134fa7c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.020080321285140562,
+  "epoch": 0.030120481927710843,
   "eval_steps": 2,
-  "global_step": 10,
+  "global_step": 15,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -125,6 +125,57 @@
       "eval_samples_per_second": 17.619,
       "eval_steps_per_second": 8.81,
       "step": 10
+    },
+    {
+      "epoch": 0.02208835341365462,
+      "grad_norm": 1.0168466567993164,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 5.7733,
+      "step": 11
+    },
+    {
+      "epoch": 0.024096385542168676,
+      "grad_norm": 1.0794020891189575,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 5.7392,
+      "step": 12
+    },
+    {
+      "epoch": 0.024096385542168676,
+      "eval_loss": 1.4653736352920532,
+      "eval_runtime": 11.9932,
+      "eval_samples_per_second": 17.51,
+      "eval_steps_per_second": 8.755,
+      "step": 12
+    },
+    {
+      "epoch": 0.02610441767068273,
+      "grad_norm": 1.0890697240829468,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 5.7144,
+      "step": 13
+    },
+    {
+      "epoch": 0.028112449799196786,
+      "grad_norm": 1.0109323263168335,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 5.9203,
+      "step": 14
+    },
+    {
+      "epoch": 0.028112449799196786,
+      "eval_loss": 1.460502028465271,
+      "eval_runtime": 11.9047,
+      "eval_samples_per_second": 17.64,
+      "eval_steps_per_second": 8.82,
+      "step": 14
+    },
+    {
+      "epoch": 0.030120481927710843,
+      "grad_norm": 1.0608059167861938,
+      "learning_rate": 0.0,
+      "loss": 6.6043,
+      "step": 15
     }
   ],
   "logging_steps": 1,
@@ -139,12 +190,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3501810870386688.0,
+  "total_flos": 5130560112427008.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null