Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45b076e7d54299cb74fa198820fa08fbab4d53ccff459784d4167e9601e66290
+oid sha256:92d52e37c41e950a2743a96a9524f6f43f4c157f4b753d783af6dec67177ab2f
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3609b181e3e5a9fbda68b5826d0fcca02340ce407741d0532e5a37156616ef54
+oid sha256:7e06435aaef2ab84b113a7005f2de02947913961c321da5e980c9ff3b9f131c0
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8030a53cb52ce93216e46a07597b4eae0f283ad8d80d8ea4871c4a953efe3987
+oid sha256:1fd7a2290f77a4159b388fe0269382f9ae2e2474e3f0daa565228958f5b5fb62
 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": 0.013043478260869565,
+  "epoch": 0.02608695652173913,
   "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": 29.217,
       "eval_steps_per_second": 14.759,
       "step": 3
+    },
+    {
+      "epoch": 0.017391304347826087,
+      "grad_norm": 18.890443801879883,
+      "learning_rate": 8e-05,
+      "loss": 5.1176,
+      "step": 4
+    },
+    {
+      "epoch": 0.021739130434782608,
+      "grad_norm": 17.343791961669922,
+      "learning_rate": 0.0001,
+      "loss": 5.3026,
+      "step": 5
+    },
+    {
+      "epoch": 0.02608695652173913,
+      "grad_norm": 17.925121307373047,
+      "learning_rate": 0.00012,
+      "loss": 6.5716,
+      "step": 6
+    },
+    {
+      "epoch": 0.02608695652173913,
+      "eval_loss": 1.0198545455932617,
+      "eval_runtime": 3.3329,
+      "eval_samples_per_second": 29.104,
+      "eval_steps_per_second": 14.702,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 569617680433152.0,
+  "total_flos": 1183052105515008.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null