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:e7d96c5ee47dfdb392edf8ec8332a7a94dc5d2bba21ebaa1fafb8e90caeaa706
+oid sha256:0dc224b999eea28dfd6fc70f9b5d14365ef6e3897f62d2f321730bf9d76c8c4b
 size 108113968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6a0d3c7959901741908b1798509afda5f097508292ee70e4c8b4dd844b640e5
+oid sha256:70b7c4ce50184ed77f6f17de67bdfc37a8e25415ead5b46108ff51d3a83af205
 size 55549892

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48fa52843170dc1e0fa84a430675df8adb90967d3ee1d05519d853f2bf671252
+oid sha256:fa55bb1211b966ee38680600e87c633649407947bf0fb7e8011fe6d5c3e8c50b
 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": 0.00916030534351145,
+  "epoch": 0.0183206106870229,
   "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": 7.282,
       "eval_steps_per_second": 3.641,
       "step": 3
+    },
+    {
+      "epoch": 0.012213740458015267,
+      "grad_norm": 1.3037679195404053,
+      "learning_rate": 8e-05,
+      "loss": 2.2116,
+      "step": 4
+    },
+    {
+      "epoch": 0.015267175572519083,
+      "grad_norm": 1.0085657835006714,
+      "learning_rate": 0.0001,
+      "loss": 1.9184,
+      "step": 5
+    },
+    {
+      "epoch": 0.0183206106870229,
+      "grad_norm": 4.906698226928711,
+      "learning_rate": 0.00012,
+      "loss": 2.8942,
+      "step": 6
+    },
+    {
+      "epoch": 0.0183206106870229,
+      "eval_loss": 2.3518502712249756,
+      "eval_runtime": 19.535,
+      "eval_samples_per_second": 7.064,
+      "eval_steps_per_second": 3.532,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 615718085197824.0,
+  "total_flos": 1231436170395648.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null