Training in progress, step 200000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1bfd0cddbf97500b804d75ee36c26ed96611659670b0b2ed6d653aee55853a2c
+oid sha256:622ffd3a7b017059677381c4957b8684c94feda5c36dd09d4c9eb745833a1cf3
 size 995605445

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:818d66022a1a0a509c6891b5f86abae01394bb56687825269a96997c1b2cce48
+oid sha256:df5e243d791ce4f65dc68bf0f3a46091fb97d6aafd2414ee9a81131404021ee0
 size 510398013

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96a0856e38453e8d42dbf78599dc74e104d8e57aa7be6994b178da4101257c60
+oid sha256:c9c10092a1e7977cf34645ee895c471f8c4d2d3bd2aa8edd2570bdd9e3a7e77a
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28597cb7c5812a82370639d69e01be9b315303a0dcf2bda300d43ca14050197f
+oid sha256:3cdc4afee694df5e30232d1b113751895a7bfe4c051ca10278bb6f9244c467f9
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 4.498532057960034,
-  "global_step": 190000,
+  "epoch": 4.735296903115826,
+  "global_step": 200000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2444,11 +2444,139 @@
       "eval_samples_per_second": 166.197,
       "eval_steps_per_second": 20.779,
       "step": 190000
+    },
+    {
+      "epoch": 4.51,
+      "learning_rate": 1.5078826909113869e-05,
+      "loss": 2.649,
+      "step": 190500
+    },
+    {
+      "epoch": 4.52,
+      "learning_rate": 1.5015689617072324e-05,
+      "loss": 2.6748,
+      "step": 191000
+    },
+    {
+      "epoch": 4.53,
+      "learning_rate": 1.495255232503078e-05,
+      "loss": 2.66,
+      "step": 191500
+    },
+    {
+      "epoch": 4.55,
+      "learning_rate": 1.4889415032989236e-05,
+      "loss": 2.6656,
+      "step": 192000
+    },
+    {
+      "epoch": 4.56,
+      "learning_rate": 1.4826277740947693e-05,
+      "loss": 2.6665,
+      "step": 192500
+    },
+    {
+      "epoch": 4.57,
+      "learning_rate": 1.4763140448906148e-05,
+      "loss": 2.6698,
+      "step": 193000
+    },
+    {
+      "epoch": 4.58,
+      "learning_rate": 1.4700003156864605e-05,
+      "loss": 2.6561,
+      "step": 193500
+    },
+    {
+      "epoch": 4.59,
+      "learning_rate": 1.463686586482306e-05,
+      "loss": 2.671,
+      "step": 194000
+    },
+    {
+      "epoch": 4.61,
+      "learning_rate": 1.4573728572781513e-05,
+      "loss": 2.6795,
+      "step": 194500
+    },
+    {
+      "epoch": 4.62,
+      "learning_rate": 1.451059128073997e-05,
+      "loss": 2.6709,
+      "step": 195000
+    },
+    {
+      "epoch": 4.63,
+      "learning_rate": 1.4447453988698425e-05,
+      "loss": 2.6818,
+      "step": 195500
+    },
+    {
+      "epoch": 4.64,
+      "learning_rate": 1.4384316696656882e-05,
+      "loss": 2.6808,
+      "step": 196000
+    },
+    {
+      "epoch": 4.65,
+      "learning_rate": 1.4321179404615337e-05,
+      "loss": 2.6767,
+      "step": 196500
+    },
+    {
+      "epoch": 4.66,
+      "learning_rate": 1.4258042112573794e-05,
+      "loss": 2.6861,
+      "step": 197000
+    },
+    {
+      "epoch": 4.68,
+      "learning_rate": 1.4194904820532249e-05,
+      "loss": 2.6694,
+      "step": 197500
+    },
+    {
+      "epoch": 4.69,
+      "learning_rate": 1.4131767528490706e-05,
+      "loss": 2.6766,
+      "step": 198000
+    },
+    {
+      "epoch": 4.7,
+      "learning_rate": 1.4068630236449159e-05,
+      "loss": 2.6597,
+      "step": 198500
+    },
+    {
+      "epoch": 4.71,
+      "learning_rate": 1.4005492944407614e-05,
+      "loss": 2.6551,
+      "step": 199000
+    },
+    {
+      "epoch": 4.72,
+      "learning_rate": 1.3942355652366071e-05,
+      "loss": 2.6514,
+      "step": 199500
+    },
+    {
+      "epoch": 4.74,
+      "learning_rate": 1.3879218360324526e-05,
+      "loss": 2.6788,
+      "step": 200000
+    },
+    {
+      "epoch": 4.74,
+      "eval_loss": 3.1263821125030518,
+      "eval_runtime": 112.9792,
+      "eval_samples_per_second": 166.155,
+      "eval_steps_per_second": 20.774,
+      "step": 200000
     }
   ],
   "max_steps": 633540,
   "num_train_epochs": 15,
-  "total_flos": 4.0274738295552e+16,
+  "total_flos": 4.2369106205952e+16,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:818d66022a1a0a509c6891b5f86abae01394bb56687825269a96997c1b2cce48
+oid sha256:df5e243d791ce4f65dc68bf0f3a46091fb97d6aafd2414ee9a81131404021ee0
 size 510398013