Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3baa951bbbfdd1188f382c335ea49151b29b4c1fb18142935ab6cba433da0dc0
+oid sha256:3aac39305042db65e185a641f36dc6b082e880a8ae99671945cd1fb5837ec2e8
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fdecc7bce3383d3a5b220e46876f4004ad2ace0aa89554c31ac6a6f13b9323b
+oid sha256:767fb7e8638a2c355928166a9abc6ac5c9b81833a2e81a3fab6e150b49245069
 size 43122580

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cf68e26f94a54bb8ae5cbe12765de6bac6a1ccb174b66646786b68d44d57d0a
+oid sha256:86152328387bf4d06e154ce72c80c1e37ad9b4670390d983a136b7723139aeec
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c8fe3c71a39000d4197cc8405349be99d4e3eb178b1ed84fbd89bec27620702
+oid sha256:8b6a20c76ee9618e0647deb8c445da5bd6342388307bcf338931fe3c22c75fe2
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70a1a52aa6601b66cd14aa6c2ab353f19e95d8c430b1673f818f682e2acf6abc
+oid sha256:f29ee702fb88b51e8b0f5ef18a0af6b3582ef2f9d5591203f8b3c2639e4a5730
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef25f629f6c4240e649191e5537010a60073d3455d6b59ae07a421ecdf15669f
+oid sha256:046b7b8139527cac471c01c3dae2e7434e9471dc6563d41a3f634f19133b5b17
 size 15024

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": 0.056074766355140186,
+  "epoch": 0.11214953271028037,
   "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": 92.663,
       "eval_steps_per_second": 12.219,
       "step": 3
+    },
+    {
+      "epoch": 0.07476635514018691,
+      "grad_norm": 1.3184479475021362,
+      "learning_rate": 8e-05,
+      "loss": 2.1899,
+      "step": 4
+    },
+    {
+      "epoch": 0.09345794392523364,
+      "grad_norm": 1.292141318321228,
+      "learning_rate": 0.0001,
+      "loss": 2.1399,
+      "step": 5
+    },
+    {
+      "epoch": 0.11214953271028037,
+      "grad_norm": 1.3748526573181152,
+      "learning_rate": 0.00012,
+      "loss": 2.1182,
+      "step": 6
+    },
+    {
+      "epoch": 0.11214953271028037,
+      "eval_loss": 1.8800315856933594,
+      "eval_runtime": 0.9805,
+      "eval_samples_per_second": 92.81,
+      "eval_steps_per_second": 12.239,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2219477097775104.0,
+  "total_flos": 4438954195550208.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null