Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91911e9fd3c2b11df120ec348dc6e066d44618c0e5d1a00c771ceda0526eb507
+oid sha256:d18a57712d2867d07fb035205b4ac7ca3c8cfd5951236f27785d893ccce1276e
 size 125040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e9d75e79277be72e020536408eaeaf3dfd54a70fda83d2a1dfe741f1134ccd6
+oid sha256:d53e4986b1498ef7e2718110d725c83956624005da2c63763f06bfcb879ec711
 size 162868

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9264abfa6d2cc5145363bf71d2fb16332b1ac4e60642a70827881d9a447c36a4
+oid sha256:af82c1f1d4ec999545a290f8875f59e0434314b9e98a3c2553c0c541daf4cdfa
 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": 0.003416856492027335,
+  "epoch": 0.00683371298405467,
   "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": 308.646,
       "eval_steps_per_second": 154.323,
       "step": 3
+    },
+    {
+      "epoch": 0.004555808656036446,
+      "grad_norm": 0.7419840097427368,
+      "learning_rate": 8e-05,
+      "loss": 44.4458,
+      "step": 4
+    },
+    {
+      "epoch": 0.0056947608200455585,
+      "grad_norm": 0.9602454900741577,
+      "learning_rate": 0.0001,
+      "loss": 44.479,
+      "step": 5
+    },
+    {
+      "epoch": 0.00683371298405467,
+      "grad_norm": 0.700503945350647,
+      "learning_rate": 0.00012,
+      "loss": 44.4369,
+      "step": 6
+    },
+    {
+      "epoch": 0.00683371298405467,
+      "eval_loss": 11.114104270935059,
+      "eval_runtime": 1.2323,
+      "eval_samples_per_second": 300.248,
+      "eval_steps_per_second": 150.124,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 50635210752.0,
+  "total_flos": 103681622016.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null