Training in progress, step 120000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c948eebbc33dfa7163a265ead1f1a9361b0c30c12a12de00dcf340d40d2658b
+oid sha256:dcc09d22e5596eeac7cbb0a1dabfeacc19af29a548e591c9f749208980b7916a
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3496297d45c4ecf853137342e06ee76ffd7a454b5f8f23c88381de10d12213d2
+oid sha256:ca3c3ce97bc1c8862c7db669723fd31e2c4926cda5ff7010a6c07f89d409cca1
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:adcae24276cfe7a6f029d01f999621482dc39224a9126d96b9666e8134968416
-size 14439
+oid sha256:7fc306b40ea32fc4b974d92fa4436f6126d03d93634b99c4944393049e4dd34d
+size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50b86582c3ae12c705a7005fed2da8884791451301066581e22169aa8046a6bd
+oid sha256:83b1dc502294b82568367d2e77a4231f6fb11b7296d845de6be2991e1953c467
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ea4115312e60b99085371b9865a77942fe890528298791f0e387803437d5ebb
+oid sha256:90c7dcc243e1aa80b2e25ba58bbf11ac2e612d08701ac3bc19fe812cf11394f0
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9811453ee080e5df1835ce925467584d500ae5c97c544e104ff63747920507e0
-size 14567
+oid sha256:b63f502697a67e82fe85208c9b5cb87051cc2490893eb283cf394fd4c0f8586c
+size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4aabac21e516317a7b98a87a94ce8a8b7afae82a6e696839a4840e30fc5507ba
+oid sha256:27556e6e847d06ad2f934e5a134bda54baf3ade1f4eea8c1e651de3a5e1bb425
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.6797226930535831,
-  "global_step": 110000,
+  "epoch": 1.8324247560584543,
+  "global_step": 120000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -820,11 +820,85 @@
       "eval_samples_per_second": 984.91,
       "eval_steps_per_second": 15.759,
       "step": 110000
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 0.00014858059266190327,
+      "loss": 0.3552,
+      "step": 111000
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 0.00014853383772619612,
+      "loss": 0.3544,
+      "step": 112000
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 0.00014848633331541967,
+      "loss": 0.3537,
+      "step": 113000
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 0.0001484380799490746,
+      "loss": 0.3524,
+      "step": 114000
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 0.00014838907815485194,
+      "loss": 0.3519,
+      "step": 115000
+    },
+    {
+      "epoch": 1.76,
+      "eval_runtime": 1.003,
+      "eval_samples_per_second": 997.001,
+      "eval_steps_per_second": 15.952,
+      "step": 115000
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 0.00014833932846862748,
+      "loss": 0.3511,
+      "step": 116000
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 0.00014828883143445582,
+      "loss": 0.3502,
+      "step": 117000
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 0.0001482375876045644,
+      "loss": 0.3493,
+      "step": 118000
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 0.0001481855975393476,
+      "loss": 0.3489,
+      "step": 119000
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 0.0001481328618073604,
+      "loss": 0.3482,
+      "step": 120000
+    },
+    {
+      "epoch": 1.83,
+      "eval_runtime": 1.0596,
+      "eval_samples_per_second": 943.744,
+      "eval_steps_per_second": 15.1,
+      "step": 120000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 7.711022142656698e+21,
+  "total_flos": 8.41202475296017e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3496297d45c4ecf853137342e06ee76ffd7a454b5f8f23c88381de10d12213d2
+oid sha256:ca3c3ce97bc1c8862c7db669723fd31e2c4926cda5ff7010a6c07f89d409cca1
 size 449471589