Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bc41ecbacabc2e3158d9c8caeda4ab1eba1fbd973253323888f732a95bdcf1c
+oid sha256:f233622deb520bb7d498a204fddb47e4f42b69baf913fbb281f4b42171804e98
 size 6804608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04532c5cb471528c311d193670ea5d983a73345f32caba191bf7ff1000c84b5f
+oid sha256:62fb16a9b23f13e89982748689d27aa0e493f54d4b2fce1e81613445cbd9a22e
 size 3633530

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db3058f8f1ee14618db74217e8eeff91e9030a2fe706f1c21688e02cd2191222
+oid sha256:d096002160b6f6344e44b161020fd5f8176aab00ff00fe8c5ea42cb9ad318a93
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
+oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0076726342710997444,
+  "epoch": 0.015345268542199489,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 79.744,
       "eval_steps_per_second": 40.114,
       "step": 3
+    },
+    {
+      "epoch": 0.010230179028132993,
+      "grad_norm": 0.3995542824268341,
+      "learning_rate": 8e-05,
+      "loss": 2.4755,
+      "step": 4
+    },
+    {
+      "epoch": 0.01278772378516624,
+      "grad_norm": 0.4776461720466614,
+      "learning_rate": 0.0001,
+      "loss": 2.6502,
+      "step": 5
+    },
+    {
+      "epoch": 0.015345268542199489,
+      "grad_norm": 0.4988251328468323,
+      "learning_rate": 0.00012,
+      "loss": 2.8217,
+      "step": 6
+    },
+    {
+      "epoch": 0.015345268542199489,
+      "eval_loss": 2.74558687210083,
+      "eval_runtime": 2.1,
+      "eval_samples_per_second": 78.571,
+      "eval_steps_per_second": 39.524,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 10287795142656.0,
+  "total_flos": 20575590285312.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null