Training in progress, step 30000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78c410b30ed46201dc76b3758a8f05ba2befb17e53aabac920b8594900bf6e8f
+oid sha256:5b82214f5a6da233cbde612bdd1f848ffc727475d410f23d11d0ef77869df202
 size 893438545

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:793325251fa149e905afc5251e0311b4cc842e9f6cbb39aa46ab80628503d14f
+oid sha256:72a1a14ed7bf6bc0725bb876cb7a38064b9cb2a4e01a8c1e6ca520325a13a6e9
 size 449471589

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:138259c5b6d4472016db54172bb7e725edf4c52d33cd44c90cb79184c02490ab
+oid sha256:b911e5c773c97f0b6494ffc61a4bccbd0595e2f25c8540a15cd988ed7205ecc7
 size 15587

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d302e2bbe5f8cc1de61c1cfd61605591d0eb14f9a715e2ddd90f5a8190314e3
+oid sha256:be94e3813e8e1c0f62960e0a57904cf2dbed90df3bbe70219beb6f9114fec94f
 size 559

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afdbfcefcd9e1661e5368ed0a7d4915dce2e8bd6a92fd4d33ed45da578d95703
+oid sha256:32b016f83d2aca2db829c6d70c41861d7f94941040995a7638b751ed5d1d2359
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.1765627720703464,
-  "global_step": 25000,
+  "epoch": 2.611875326484416,
+  "global_step": 30000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -346,11 +346,79 @@
       "eval_samples_per_second": 306.184,
       "eval_steps_per_second": 4.838,
       "step": 25000
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 8.698878062256518e-05,
+      "loss": 0.4355,
+      "step": 25500
+    },
+    {
+      "epoch": 2.26,
+      "learning_rate": 8.647303945562088e-05,
+      "loss": 0.4346,
+      "step": 26000
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 8.594962916800582e-05,
+      "loss": 0.435,
+      "step": 26500
+    },
+    {
+      "epoch": 2.35,
+      "learning_rate": 8.54186789033765e-05,
+      "loss": 0.434,
+      "step": 27000
+    },
+    {
+      "epoch": 2.39,
+      "learning_rate": 8.488031966576593e-05,
+      "loss": 0.4341,
+      "step": 27500
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 8.433468428726034e-05,
+      "loss": 0.4341,
+      "step": 28000
+    },
+    {
+      "epoch": 2.48,
+      "learning_rate": 8.378190739522489e-05,
+      "loss": 0.4336,
+      "step": 28500
+    },
+    {
+      "epoch": 2.52,
+      "learning_rate": 8.322212537908629e-05,
+      "loss": 0.4323,
+      "step": 29000
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 8.265547635668083e-05,
+      "loss": 0.4331,
+      "step": 29500
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 8.208325351258954e-05,
+      "loss": 0.4318,
+      "step": 30000
+    },
+    {
+      "epoch": 2.61,
+      "eval_loss": 0.4114779233932495,
+      "eval_runtime": 17.3867,
+      "eval_samples_per_second": 287.576,
+      "eval_steps_per_second": 4.544,
+      "step": 30000
     }
   ],
   "max_steps": 100000,
   "num_train_epochs": 9,
-  "total_flos": 1.1774280960596666e+21,
+  "total_flos": 1.4129211634244282e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:793325251fa149e905afc5251e0311b4cc842e9f6cbb39aa46ab80628503d14f
+oid sha256:72a1a14ed7bf6bc0725bb876cb7a38064b9cb2a4e01a8c1e6ca520325a13a6e9
 size 449471589