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:af0ea2e2f9ea8792ffadbe4a61b888e385d877a6ebbeacd2513fc896c6df4551
+oid sha256:783e96a426e6357081b6696794e7f36a47df68efe8322504801d3314e4cb296d
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e3c8a657aad7cf2d1a6a428debf10d105bec4b8796528f0f691a7eb1caead13
+oid sha256:60c5360f611de6ffac18768d08cdfb60b9fe454f35132edc1b542cf2a43c5a6b
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cf86cd5b19b8056a2759fc36b0c4f0323fb9c04403c19df65bcd5311b20dea5
+oid sha256:693d65ff7d3abbbb13c7ee57d38fa6e7fa5181ebaaabad321dd22b54929bbad4
 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": 8.595065000179063e-05,
+  "epoch": 0.00017190130000358127,
   "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": 21.067,
       "eval_steps_per_second": 10.534,
       "step": 3
+    },
+    {
+      "epoch": 0.00011460086666905418,
+      "grad_norm": 0.3214547038078308,
+      "learning_rate": 8e-05,
+      "loss": 0.3464,
+      "step": 4
+    },
+    {
+      "epoch": 0.00014325108333631772,
+      "grad_norm": 0.4778994619846344,
+      "learning_rate": 0.0001,
+      "loss": 0.3377,
+      "step": 5
+    },
+    {
+      "epoch": 0.00017190130000358127,
+      "grad_norm": 0.4470870792865753,
+      "learning_rate": 0.00012,
+      "loss": 0.4031,
+      "step": 6
+    },
+    {
+      "epoch": 0.00017190130000358127,
+      "eval_loss": 0.4111326336860657,
+      "eval_runtime": 697.9828,
+      "eval_samples_per_second": 21.056,
+      "eval_steps_per_second": 10.529,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 949861251809280.0,
+  "total_flos": 1899722503618560.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null