Training in progress, step 910000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81603416f1fba3109b9ef2dfed9df589999e06f1186e2baeac09426d5454ae3d
+oid sha256:dcd026b7ddbbed9854cf4a848e8d10565ecae8551444b93cf80516c2a3075094
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cd0588845ddc4a31c9c47550dec41eb37349d2edd4e1f34356e1f993b492ba0
+oid sha256:8c1213c78566dba45a4dbe4cbf12671b2071e92687a82a7bd671a18dd4693188
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f495dfd7f4ccee04d72bad0e351a96e4d86b89643197cb94dfee5e43013e7b2
-size 14439
+oid sha256:23bff7c83371f4786566c176465b52f06fe8e3280f8cace7df94d70a8a5b2164
+size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a3ab375a848ecaefff3706d2c692ac9259621d2aa93953ba9d5f4510dca87b7
+oid sha256:7220d15ed34c785cde537b4220883e048554a1408ecd7fe46faf0069997fc88e
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48bc8ea8a56da3a164d01716edb5b450bdffa75fb03183f592780d30cdcccc55
+oid sha256:52361dad9976f354f626771e1b0dbf34f1017e0982c95cf304b85aa55d90473b
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bef8a52198e713e41af5f2aacfd75864c1e5d1bcaad410e37c104450edb03f2
+oid sha256:242dcb89ecc86bf6b74de9a6782f0aca020ba83ca594d7f0c60637dcb70148d3
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa624c96f92eaad028a188cf78acc34c38cdc88db165dfecd04176965e65555e
+oid sha256:68bd93c5df85b9ef6b8dfb004005413abc49b194d979c692716ee25211f1498f
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 13.743185670438407,
-  "global_step": 900000,
+  "epoch": 13.89588773344328,
+  "global_step": 910000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6666,11 +6666,85 @@
       "eval_samples_per_second": 1325.982,
       "eval_steps_per_second": 21.216,
       "step": 900000
+    },
+    {
+      "epoch": 13.76,
+      "learning_rate": 1.3717991925554562e-05,
+      "loss": 0.2308,
+      "step": 901000
+    },
+    {
+      "epoch": 13.77,
+      "learning_rate": 1.3643915619574529e-05,
+      "loss": 0.2305,
+      "step": 902000
+    },
+    {
+      "epoch": 13.79,
+      "learning_rate": 1.35705649731021e-05,
+      "loss": 0.2304,
+      "step": 903000
+    },
+    {
+      "epoch": 13.8,
+      "learning_rate": 1.3497940788288195e-05,
+      "loss": 0.2301,
+      "step": 904000
+    },
+    {
+      "epoch": 13.82,
+      "learning_rate": 1.3426043859339253e-05,
+      "loss": 0.2304,
+      "step": 905000
+    },
+    {
+      "epoch": 13.82,
+      "eval_runtime": 0.9802,
+      "eval_samples_per_second": 1020.243,
+      "eval_steps_per_second": 16.324,
+      "step": 905000
+    },
+    {
+      "epoch": 13.83,
+      "learning_rate": 1.3354874972508582e-05,
+      "loss": 0.2302,
+      "step": 906000
+    },
+    {
+      "epoch": 13.85,
+      "learning_rate": 1.3284434906087695e-05,
+      "loss": 0.2303,
+      "step": 907000
+    },
+    {
+      "epoch": 13.87,
+      "learning_rate": 1.3214724430397915e-05,
+      "loss": 0.2304,
+      "step": 908000
+    },
+    {
+      "epoch": 13.88,
+      "learning_rate": 1.314574430778182e-05,
+      "loss": 0.2302,
+      "step": 909000
+    },
+    {
+      "epoch": 13.9,
+      "learning_rate": 1.3077495292594966e-05,
+      "loss": 0.2305,
+      "step": 910000
+    },
+    {
+      "epoch": 13.9,
+      "eval_runtime": 0.7262,
+      "eval_samples_per_second": 1377.03,
+      "eval_steps_per_second": 22.032,
+      "step": 910000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 6.309014950845309e+22,
+  "total_flos": 6.379115211875656e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cd0588845ddc4a31c9c47550dec41eb37349d2edd4e1f34356e1f993b492ba0
+oid sha256:8c1213c78566dba45a4dbe4cbf12671b2071e92687a82a7bd671a18dd4693188
 size 449471589