Training in progress, step 100, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca5ae10db168677b2a3c9eebebb9f8c7f9b9d67457d37ffa9c3acda730924ede
+oid sha256:c3d4c86dbc3a809d6bdc35e80da94e44289853f47f3c4e8bc28bb197206757d0
 size 723674912

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fce942f56022b1c968835cb5703df1ddb7bb2d9c6269c456723dbdb59672d7c
+oid sha256:152992c22320b5355e945dfb4a4cba99cfb4bf09b642dbac9c3009149011352d
 size 735625370

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8e86174b3eb32925060e9953680fbcda12f487778e2fa23373bff16bb360a64
+oid sha256:65fc5493cd95cc4a525582d7144fab8c2fb7ccb5f192423671fe2e1c71f9588c
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96e7dd869a6e1b32bc9520ed4dad315337bd74e7bba1905b1527b70f353d1ff6
+oid sha256:1e7cda19f7cb3579408e9f405862a0136ef9f921b9602ef040b683708565b31e
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cdef07c8fb03613426123802d3ee28840d50c7dc4d30cb68fc9cabc31660adb
+oid sha256:35761c9ae1453a385e31327d4717208e814e94ccb377326730a4c7b214baa671
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24cc5299af352f51d11766db1f1a250378308cfbc684430ac64ca9d7b85e55c6
+oid sha256:6a35cbf7b65c1a64e50166e0bb259917c6b81f8e9db674c5beb450f633f0b85b
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7c81ebb017017feee3c6c3f2477294c6f8e1ba38c8568a1c58d53f7e2c4e60d
+oid sha256:3fc7800513a1b4dd006c457152c700dd768bb49ee4ed8e4d9665a4e42095b054
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 10.0,
+  "epoch": 12.5,
   "eval_steps": 20,
-  "global_step": 80,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -103,6 +103,28 @@
       "eval_samples_per_second": 305.813,
       "eval_steps_per_second": 3.464,
       "step": 80
+    },
+    {
+      "epoch": 11.25,
+      "grad_norm": 0.1337890625,
+      "learning_rate": 0.00012454854871407994,
+      "loss": 2.0551,
+      "step": 90
+    },
+    {
+      "epoch": 12.5,
+      "grad_norm": 0.14453125,
+      "learning_rate": 0.00010825793454723325,
+      "loss": 2.0298,
+      "step": 100
+    },
+    {
+      "epoch": 12.5,
+      "eval_loss": 2.0621085166931152,
+      "eval_runtime": 5.0999,
+      "eval_samples_per_second": 294.32,
+      "eval_steps_per_second": 3.333,
+      "step": 100
     }
   ],
   "logging_steps": 10,
@@ -122,7 +144,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.8455506955730944e+16,
+  "total_flos": 3.556938369466368e+16,
   "train_batch_size": 23,
   "trial_name": null,
   "trial_params": null