Training in progress, step 140, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a4088d19f3feafeea0ba308088b23e333d4e2e8212508984ad279a2718b463c
+oid sha256:8e740ffbbdfadc8bf234148d76ac0ed60381ced5dfbd658d49b9b798316874f7
 size 723674912

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:862ec37d7402f06eca8c5631cb47313d0e3b86f327a3adab6ed60c7a6dac0bd7
+oid sha256:4a2f1ddbd3db8cdaf06e7423793917493328e0a8cb44ed0e8d28035287cca420
 size 735625370

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de84365e523b671148dee4ef5a415c09b66cbaaf3ce3aaba61c6acc0b991d242
+oid sha256:3fc92af0f7629ac7a872f96d896483407615467dfa6d229c0bce0291923d54d2
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cdb319ce950173c204205964e35c8665d6abc97e1525ad1b79edde97bcc6f7a6
+oid sha256:c01fd1d8f82dc5b8d4b0f55c2ab8164cf309fea692e13308378886e8a4c284e0
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8756cd4016ed8d5c332f8209ba3b0c43efab2992e08002c551d548df333245fb
+oid sha256:ce04f332c8a6301f4e0e3529f0f24d4ecc77280aa968eb8788a8dbde321f8780
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3754437784f92a43a34bbcf6fc157d6c11ae9b99c41e9276f5acb6ebff008234
+oid sha256:4cdd0d6703b8a4673eb5f0f1700b967c31563a5843fa11ee1bc8ac7bd3c25784
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c529fddb481006b1e3405be545b49efe52a1e58e5f5201db70a3d1286475c0e4
+oid sha256:d8ad7d13c349dc6d2db1696e8cfa744a9b690a7740ecbd387461ee1d69ba8e9e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 15.0,
+  "epoch": 17.5,
   "eval_steps": 20,
-  "global_step": 120,
+  "global_step": 140,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -147,6 +147,28 @@
       "eval_samples_per_second": 292.227,
       "eval_steps_per_second": 3.31,
       "step": 120
+    },
+    {
+      "epoch": 16.25,
+      "grad_norm": 0.130859375,
+      "learning_rate": 5.983045753470308e-05,
+      "loss": 2.0127,
+      "step": 130
+    },
+    {
+      "epoch": 17.5,
+      "grad_norm": 0.1376953125,
+      "learning_rate": 4.530518418775733e-05,
+      "loss": 2.0188,
+      "step": 140
+    },
+    {
+      "epoch": 17.5,
+      "eval_loss": 2.0686135292053223,
+      "eval_runtime": 5.3391,
+      "eval_samples_per_second": 281.135,
+      "eval_steps_per_second": 3.184,
+      "step": 140
     }
   ],
   "logging_steps": 10,
@@ -166,7 +188,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.268326043359642e+16,
+  "total_flos": 4.979713717252915e+16,
   "train_batch_size": 23,
   "trial_name": null,
   "trial_params": null