Training in progress, step 80000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0d611070fc96c13fe2a726a75aa89fbb18b267a55a563cdceaf1c3fbade3f8c
+oid sha256:ff5c6edbd27558aca49d30391d1ef6740f42d89e02202741bfa6556c5bb200e6
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26811078f796ab6f92af5a3940b414f53cb4f1a1f7777c0f34bdde158fb49f0e
+oid sha256:a1666258a1f724f902b9aa295ec67f13a120dd77f80fd4e6bc4d68349a651a63
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff190ea62daf1e533d229f2cbdc2bf1b0b91f1b54ad94055b49d136687089c2b
-size 14439
+oid sha256:67d9b61cee8ca67c27f0f3d2f6e201039abcc50fe9c69747f98360b11e440474
+size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40b1051d2935e5a6ad2bc776aeb5c7effef95653590b063d7af64113e86e7198
+oid sha256:8a497315615827dbfe07ef4ef54afba40b23c55667dfa82ac40626574a432d00
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca733adc62d3884a07b0f3bff0700e4d418d28a780a35e3db8b9f7f1147beb15
+oid sha256:7f62de7b3720d73b36506a2be2c357e852a008b86421c13562a927e573a51594
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f9ae59fc5fa85627e7d16c864bbec928ea1cdb8c2fa89705bb65d8bdd8ab7fb
-size 14503
+oid sha256:b65baacae1e9b6120b362e0290a5ce659aa309c6bbced410beb869eaf2627764
+size 14439

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7c802ff93fc9d67d63f3e03f7bd5fd1c7e4a71a3faef71bb4d686a1c5885c38
+oid sha256:e52a6dd6fc2ba6933bc667fca14386a68b07572a9b1700ef8ab0b34bba18efa7
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.0689144410340983,
-  "global_step": 70000,
+  "epoch": 1.2216165040389695,
+  "global_step": 80000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -524,11 +524,85 @@
       "eval_samples_per_second": 881.784,
       "eval_steps_per_second": 14.109,
       "step": 70000
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.00014983127298555198,
+      "loss": 0.4114,
+      "step": 71000
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.00014981482840217632,
+      "loss": 0.4086,
+      "step": 72000
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.00014979762033502262,
+      "loss": 0.4066,
+      "step": 73000
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.00014977964897227547,
+      "loss": 0.4042,
+      "step": 74000
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.00014976091451046687,
+      "loss": 0.402,
+      "step": 75000
+    },
+    {
+      "epoch": 1.15,
+      "eval_runtime": 1.0331,
+      "eval_samples_per_second": 967.957,
+      "eval_steps_per_second": 15.487,
+      "step": 75000
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.00014974141715447386,
+      "loss": 0.3999,
+      "step": 76000
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.00014972115711751644,
+      "loss": 0.398,
+      "step": 77000
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.00014970013462115505,
+      "loss": 0.3971,
+      "step": 78000
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 0.00014967834989528843,
+      "loss": 0.3942,
+      "step": 79000
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.00014965580317815078,
+      "loss": 0.3926,
+      "step": 80000
+    },
+    {
+      "epoch": 1.22,
+      "eval_runtime": 1.084,
+      "eval_samples_per_second": 922.521,
+      "eval_steps_per_second": 14.76,
+      "step": 80000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 4.907011701442813e+21,
+  "total_flos": 5.608014311746284e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26811078f796ab6f92af5a3940b414f53cb4f1a1f7777c0f34bdde158fb49f0e
+oid sha256:a1666258a1f724f902b9aa295ec67f13a120dd77f80fd4e6bc4d68349a651a63
 size 449471589