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:ef05137894b49f930f8aab7cb09d95131b398f19db49148257218bc739507715
+oid sha256:c3dfcd65846721527933efd65966afc003eb7cbd4c5955c085d396fae07eae26
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:421d5e3ab843b4975799b068a889cc53610d520d2677d68a2195d7cd13b2b339
+oid sha256:deb48d5e8eed6149592b84babb8248d5f948aba6b333b9d5d96eaab0e74703ef
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5957b1c5ddef9a4589aa573dbaa93db587986b4a45b1eaced44d7e1affcd3ff9
+oid sha256:cd4b54f7345bbcce1595809d79d03f9645e1cdb1a732503f567a12164b7e76ad
 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": 0.0012823252831801668,
+  "epoch": 0.0025646505663603335,
   "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": 11.097,
       "eval_steps_per_second": 5.554,
       "step": 3
+    },
+    {
+      "epoch": 0.0017097670442402222,
+      "grad_norm": 1.0189697742462158,
+      "learning_rate": 8e-05,
+      "loss": 6.5502,
+      "step": 4
+    },
+    {
+      "epoch": 0.0021372088053002777,
+      "grad_norm": 0.8076102137565613,
+      "learning_rate": 0.0001,
+      "loss": 6.9798,
+      "step": 5
+    },
+    {
+      "epoch": 0.0025646505663603335,
+      "grad_norm": 0.9094170928001404,
+      "learning_rate": 0.00012,
+      "loss": 7.7738,
+      "step": 6
+    },
+    {
+      "epoch": 0.0025646505663603335,
+      "eval_loss": 1.8097198009490967,
+      "eval_runtime": 88.8832,
+      "eval_samples_per_second": 11.082,
+      "eval_steps_per_second": 5.547,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1899722503618560.0,
+  "total_flos": 3799445007237120.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null