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:c80a1b058919858e51ce0996ae5319f24c00ca8cf762e7584dd684147fcc1e90
+oid sha256:e5a662cf0d698b2160e7c2d951b2e7980570d88aba9ddedaccc6ea265e083495
 size 101752088

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca1a1dc5f7f224786e1c1ea7ce6fa42d05edd1a6d1e18f57d70199ad6389e58d
+oid sha256:abc2c85e02953fbfd03308fa3f1857cffd7d9e6a00b49c6d551534aa884128bf
 size 52046596

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2aa2a27ca4627fc54b3bad9c93059229d8d3db9053b050855b4c7904698913f2
+oid sha256:636274c6e62fd2fc06507e9257836f6068e600de02c02f4ed1fdb7155a1b6608
 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": 0.00022987184644560657,
+  "epoch": 0.00045974369289121313,
   "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": 3.662,
       "eval_steps_per_second": 1.831,
       "step": 3
+    },
+    {
+      "epoch": 0.00030649579526080876,
+      "grad_norm": 2.075087070465088,
+      "learning_rate": 8e-05,
+      "loss": 0.8706,
+      "step": 4
+    },
+    {
+      "epoch": 0.00038311974407601095,
+      "grad_norm": 1.9129090309143066,
+      "learning_rate": 0.0001,
+      "loss": 0.6452,
+      "step": 5
+    },
+    {
+      "epoch": 0.00045974369289121313,
+      "grad_norm": 1.933599591255188,
+      "learning_rate": 0.00012,
+      "loss": 0.4879,
+      "step": 6
+    },
+    {
+      "epoch": 0.00045974369289121313,
+      "eval_loss": 0.34602582454681396,
+      "eval_runtime": 1500.8477,
+      "eval_samples_per_second": 3.661,
+      "eval_steps_per_second": 1.831,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1975615204884480.0,
+  "total_flos": 3951230409768960.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null