Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1687dca0f285498e10df6e68e2f33010fa41444585f80177769ed0158230c0ed
+oid sha256:b85537759d09cf64fdf373a945587f39e5e1ca9916e892a42ac2e1ad4e875405
 size 6804608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39b1bcf84dd29e633653e01d309eb94fc9feddeffd5d51b7e0b579cbd5f508c3
+oid sha256:96d3ea1fdeb5f852a8e2dd418a908aa9e12896272a637a10d50e684e7f79fc3d
 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": 0.0012830107986742223,
+  "epoch": 0.0025660215973484445,
   "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": 112.518,
       "eval_steps_per_second": 56.316,
       "step": 3
+    },
+    {
+      "epoch": 0.0017106810648989629,
+      "grad_norm": 0.8007542490959167,
+      "learning_rate": 8e-05,
+      "loss": 3.8971,
+      "step": 4
+    },
+    {
+      "epoch": 0.0021383513311237037,
+      "grad_norm": 0.7359699010848999,
+      "learning_rate": 0.0001,
+      "loss": 3.5116,
+      "step": 5
+    },
+    {
+      "epoch": 0.0025660215973484445,
+      "grad_norm": 0.7051669955253601,
+      "learning_rate": 0.00012,
+      "loss": 3.4093,
+      "step": 6
+    },
+    {
+      "epoch": 0.0025660215973484445,
+      "eval_loss": 3.4572508335113525,
+      "eval_runtime": 8.9288,
+      "eval_samples_per_second": 110.317,
+      "eval_steps_per_second": 55.215,
+      "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