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:d66f1b6e59520aef3ebf7e7d6be308f91668f673a0c2554c5736fae74106c02c
+oid sha256:8a2d7c21d35acbf58f8b72dfc3992337183e070cc6418e2330f9028043b52ba5
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d17b869af3ddd80634257859e5e9b53c8edf251b6187719f3e0e2a7701bf6f76
+oid sha256:7ec0918ef969673d29ab1e19f9b9f14797cdc7bcd448677fc6bb748fb3544f70
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3618547b48ff97cc5cefa7e08111f87f49a1f7d62a966879e1442a81dad2112
+oid sha256:14b1bd67607eba8ddf5ef8c66ccfdfd887cd59a4ae82f1bdd8f67a050c38c0c9
 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": 0.10084033613445378,
+  "epoch": 0.20168067226890757,
   "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": 20.667,
       "eval_steps_per_second": 11.128,
       "step": 3
+    },
+    {
+      "epoch": 0.13445378151260504,
+      "grad_norm": 11.628034591674805,
+      "learning_rate": 8e-05,
+      "loss": 1.2652,
+      "step": 4
+    },
+    {
+      "epoch": 0.16806722689075632,
+      "grad_norm": 11.16609001159668,
+      "learning_rate": 0.0001,
+      "loss": 0.6447,
+      "step": 5
+    },
+    {
+      "epoch": 0.20168067226890757,
+      "grad_norm": 31.83843421936035,
+      "learning_rate": 0.00012,
+      "loss": 0.3547,
+      "step": 6
+    },
+    {
+      "epoch": 0.20168067226890757,
+      "eval_loss": 0.013815270736813545,
+      "eval_runtime": 0.6335,
+      "eval_samples_per_second": 20.522,
+      "eval_steps_per_second": 11.05,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 525800935784448.0,
+  "total_flos": 1051601871568896.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null