Training in progress, step 1240, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22aa8c039d0be9a3c988facf84625571134d37cda476dfb65d98532416555fe4
+oid sha256:7a7a5bf2ae53fe913692899a49310566217dbeffbb0199ff9046888fb5aa7575
 size 2433024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff4dbb252d5ebeffba6f21f8f84c970e70325f1ed27556618e23cfc59b40ad4f
+oid sha256:5b51ee5c39f2196a17052a3369869248cbff6bb81824726e673d7bacb4845000
 size 2498406

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8ca8a36414e90dd5ba456c333f960e4889ffb54999d5803cb989c580c8cd717
+oid sha256:a69f6ea192cfcf54ef28bb2d6bd807102ec49e655245cd88a8999a1025beaa56
 size 15984

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f0d401f661ee31f2b765dcd2b32c58ff6fac5ec7dffb7f7ab574aa7b39adad9
+oid sha256:cd5bf2b6b2f2b239cbf378c9ab279dbd312ccd339731dbb40b178c5d2117f1fa
 size 15984

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:852aa6ce51e35f784a4dc0ec9d5711e42c32f8d80ac14d6387fd99a96cb20be9
+oid sha256:bc3d6b5de9f89ae92adeb3ebb45551760dedacf84ef470629b9572c81c7e5e15
 size 15984

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed8b4821ecf65ce0ec23d8413389d2f0386e72d57248abf4db5d646f8e2d49fb
+oid sha256:8a659c65d62a0ad4ef2400d4a9efa53bb95f33c9a3510b01c06df806373098fd
 size 15984

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca81e9e996d0a71d202120d863a18b550eb8c713480df1e52307bfd9b3cc6ce3
+oid sha256:7945d23ad3f18f8d933786bc7ca2663bfc4a07a89b86602528c15c8de525cba4
 size 15984

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a81c9d10706052a5945cb04e2d871e4de45e07953c5c957c59f663d6b1cb94f
+oid sha256:e3564e5e1fb5118c052847f294bdd8157abfa1387eac82f725487e3fb9285512
 size 15984

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d62eb2d573e4666268810fad55dc5ad08bca6def78acee1ff9463881b2cf7628
+oid sha256:cd61a764da978cdc05855ec977013888fcda81d8e3f693f0b43c1fa27207c8cf
 size 15984

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11f10650ff981eaf0f064d2744bd6a541b50f4a191760c1885276196f11a060b
+oid sha256:c21d6eb44e4c3a4a2aa63996253ecd1b46d24a99d863d3828abc8a3058eb6753
 size 15984

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:427276ae77d918ee2b880ea4152618640d39ea76588856ca2cd62fe2ab8b83d7
+oid sha256:cd12f9f53e74c951a51712fa65ed54e535568d6d68567892b5b94a3a28396fca
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.4201183431952662,
+  "epoch": 1.467455621301775,
   "eval_steps": 20,
-  "global_step": 1200,
+  "global_step": 1240,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1335,6 +1335,50 @@
       "eval_samples_per_second": 423.301,
       "eval_steps_per_second": 26.492,
       "step": 1200
+    },
+    {
+      "epoch": 1.4319526627218935,
+      "grad_norm": 0.451171875,
+      "learning_rate": 0.0001135169494631497,
+      "loss": 10.4216,
+      "step": 1210
+    },
+    {
+      "epoch": 1.4437869822485208,
+      "grad_norm": 0.62890625,
+      "learning_rate": 0.00011220516908034601,
+      "loss": 10.4063,
+      "step": 1220
+    },
+    {
+      "epoch": 1.4437869822485208,
+      "eval_loss": 10.49565315246582,
+      "eval_runtime": 3.5534,
+      "eval_samples_per_second": 422.698,
+      "eval_steps_per_second": 26.454,
+      "step": 1220
+    },
+    {
+      "epoch": 1.4556213017751478,
+      "grad_norm": 0.5,
+      "learning_rate": 0.00011089125314635726,
+      "loss": 10.4023,
+      "step": 1230
+    },
+    {
+      "epoch": 1.467455621301775,
+      "grad_norm": 0.494140625,
+      "learning_rate": 0.00010957543155842702,
+      "loss": 10.3866,
+      "step": 1240
+    },
+    {
+      "epoch": 1.467455621301775,
+      "eval_loss": 10.491253852844238,
+      "eval_runtime": 3.6425,
+      "eval_samples_per_second": 412.352,
+      "eval_steps_per_second": 25.806,
+      "step": 1240
     }
   ],
   "logging_steps": 10,
@@ -1354,7 +1398,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 470216540160.0,
+  "total_flos": 485882265600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null