Training in progress, step 130000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dcc09d22e5596eeac7cbb0a1dabfeacc19af29a548e591c9f749208980b7916a
+oid sha256:eeef6904cfa32f848b9f1346c4e3c74b0fca915a351a8997e9e3c00ba9dcbbc5
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca3c3ce97bc1c8862c7db669723fd31e2c4926cda5ff7010a6c07f89d409cca1
+oid sha256:dd16d9355565127d935e0581e06272701548caedebf90cbf8e7ec4700d308c92
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7fc306b40ea32fc4b974d92fa4436f6126d03d93634b99c4944393049e4dd34d
+oid sha256:0c3369fb2b68cab39ce1c39a70e82cbae407ebef20a3614cae5eb0b8e29d67bb
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83b1dc502294b82568367d2e77a4231f6fb11b7296d845de6be2991e1953c467
+oid sha256:adc589057b5ab70a677240ea7ff1b31050aa971f7175362abbce011dcf3e27e4
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90c7dcc243e1aa80b2e25ba58bbf11ac2e612d08701ac3bc19fe812cf11394f0
+oid sha256:a41a3d1e1a810c6ca0c122b02d703e10618433c01e7c57fdc5c7f1070e2b8072
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b63f502697a67e82fe85208c9b5cb87051cc2490893eb283cf394fd4c0f8586c
+oid sha256:1078dca16195c4c6a10dd246658bec7f4ef493b51f155eaecbd40e7b74829373
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27556e6e847d06ad2f934e5a134bda54baf3ade1f4eea8c1e651de3a5e1bb425
+oid sha256:0714a313dd4ce4e99c82bf70e5eccb41f6003fe208bd22b2e683fd5e729c762a
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.8324247560584543,
-  "global_step": 120000,
+  "epoch": 1.9851268190633256,
+  "global_step": 130000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -894,11 +894,85 @@
       "eval_samples_per_second": 943.744,
       "eval_steps_per_second": 15.1,
       "step": 120000
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 0.0001480793809853123,
+      "loss": 0.3478,
+      "step": 121000
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 0.00014802515565806107,
+      "loss": 0.3468,
+      "step": 122000
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 0.00014797018641860612,
+      "loss": 0.346,
+      "step": 123000
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 0.0001479144738680823,
+      "loss": 0.3474,
+      "step": 124000
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 0.00014785801861575312,
+      "loss": 0.3447,
+      "step": 125000
+    },
+    {
+      "epoch": 1.91,
+      "eval_runtime": 0.9375,
+      "eval_samples_per_second": 1066.699,
+      "eval_steps_per_second": 17.067,
+      "step": 125000
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 0.00014780082127900416,
+      "loss": 0.3439,
+      "step": 126000
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 0.00014774288248333635,
+      "loss": 0.3436,
+      "step": 127000
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 0.00014768420286235908,
+      "loss": 0.3429,
+      "step": 128000
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 0.00014762478305778328,
+      "loss": 0.3422,
+      "step": 129000
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 0.0001475646237194144,
+      "loss": 0.3414,
+      "step": 130000
+    },
+    {
+      "epoch": 1.99,
+      "eval_runtime": 1.0085,
+      "eval_samples_per_second": 991.553,
+      "eval_steps_per_second": 15.865,
+      "step": 130000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 8.41202475296017e+21,
+  "total_flos": 9.113027363263641e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca3c3ce97bc1c8862c7db669723fd31e2c4926cda5ff7010a6c07f89d409cca1
+oid sha256:dd16d9355565127d935e0581e06272701548caedebf90cbf8e7ec4700d308c92
 size 449471589