Training in progress, step 80, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a463551cfccc403e359cad4ddd0c8801acb38014e1a5802c0957bd2b5999bfc
+oid sha256:98be32f4a41642649aacca5df192eaa4c2826f0d9b4b944b1ce52ef184b53627
 size 324583112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57ba4db594717dc4c7b9109bfe438939da85fc8edf72215115f2a3f0f905ce1c
+oid sha256:1220761571a71ca2bac986f5ea33b5cc8f2540e097cd4c51f33c54405af4585a
 size 330479994

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0df10be429c2412198f2c4c684866a8c921cbd0d9ee4c865077476da07bda410
+oid sha256:9906b173df03663b222bd12a0e83af5aaa020a12d4ad3b4f49197437057c696b
 size 15984

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b14d8363b71c1e824421bf14a513f0f951f1c6c9b9494dcedc75b3fa1fecea91
+oid sha256:b7bf7c9d7fc97693b96ee7a514a4d88728c8624bc298bf36b68fd64703b6ce38
 size 15984

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0d27a8e9aed69fdd3b729f8cbf6300af5e0e26e9226d0e2307b0cf80aff9030
+oid sha256:cba90fd12df41e2a3afe0aa9bdbcb01ea64e70a37cf6d3f1b6f819528d9eedb2
 size 15984

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23de9e35ad029c7a59ff383920fe892474d8f295c2e2f82ec3e6f109f3f96960
+oid sha256:3f677ceac78336a23596ad2dfff49115dd4f2798e6c718f3d9a417036aecc78d
 size 15984

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50724f43561b5c511c4e37bb1b8ec7e620ff22332c4f39576452e56a9e02d18d
+oid sha256:1b66cb249efdcbeae07a93ab18308b0dad6ab1938b8cda1783930dd7ca16e400
 size 15984

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f8d108db37b78249e3b0beb22f6120e06fd369dd9fbaa19526994e040db5f9d
+oid sha256:a32fc5b45250ceb9579d6cdb22a9de146f720394a5fb1a94da8455a621d02420
 size 15984

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e62597393912992a3de2b36aa1663274b75b96f6525f5504e64377c5049c51e
+oid sha256:bdaa72ece53788894cbf7d690659103118093c50cbe7ebcc4ad29ce77864063c
 size 15984

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b1f0a5c61bcbceb46a2a335e00a59c951081a94126a8ae4cc9a9102e012eb65
+oid sha256:2e1077a981f60bb0c73ac0edeec6a361fda9845f8d5236c4bc77fda2663cf80d
 size 15984

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea54818dbc15bd81d4941b71d5e2806c555d1a733f768c00c5f1a670e0a08fb1
+oid sha256:6fce9536ff5f950cceb3fa69a1e2f266b5d6de86d1ea82239294fb327d0664db
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.047337278106508875,
+  "epoch": 0.09467455621301775,
   "eval_steps": 20,
-  "global_step": 40,
+  "global_step": 80,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,54 +11,98 @@
     {
       "epoch": 0.001183431952662722,
       "eval_loss": 3.952164649963379,
-      "eval_runtime": 2.9027,
-      "eval_samples_per_second": 517.445,
-      "eval_steps_per_second": 32.383,
+      "eval_runtime": 2.765,
+      "eval_samples_per_second": 543.21,
+      "eval_steps_per_second": 33.996,
       "step": 1
     },
     {
       "epoch": 0.011834319526627219,
-      "grad_norm": 1576.0,
+      "grad_norm": 1560.0,
       "learning_rate": 1.6000000000000003e-05,
-      "loss": 3.7155,
+      "loss": 3.7217,
       "step": 10
     },
     {
       "epoch": 0.023668639053254437,
-      "grad_norm": 720.0,
+      "grad_norm": 588.0,
       "learning_rate": 3.2000000000000005e-05,
-      "loss": 3.7048,
+      "loss": 3.6889,
       "step": 20
     },
     {
       "epoch": 0.023668639053254437,
-      "eval_loss": 3.747896671295166,
-      "eval_runtime": 2.7869,
-      "eval_samples_per_second": 538.942,
-      "eval_steps_per_second": 33.729,
+      "eval_loss": 3.7026865482330322,
+      "eval_runtime": 2.7814,
+      "eval_samples_per_second": 540.023,
+      "eval_steps_per_second": 33.796,
       "step": 20
     },
     {
       "epoch": 0.03550295857988166,
-      "grad_norm": 1440.0,
+      "grad_norm": 1104.0,
       "learning_rate": 4.8e-05,
-      "loss": 3.7125,
+      "loss": 3.6835,
       "step": 30
     },
     {
       "epoch": 0.047337278106508875,
-      "grad_norm": 1032.0,
+      "grad_norm": 728.0,
       "learning_rate": 6.400000000000001e-05,
-      "loss": 3.6987,
+      "loss": 3.6239,
       "step": 40
     },
     {
       "epoch": 0.047337278106508875,
-      "eval_loss": 4.0221028327941895,
-      "eval_runtime": 2.8056,
-      "eval_samples_per_second": 535.36,
-      "eval_steps_per_second": 33.505,
+      "eval_loss": 3.7313880920410156,
+      "eval_runtime": 2.7224,
+      "eval_samples_per_second": 551.714,
+      "eval_steps_per_second": 34.528,
       "step": 40
+    },
+    {
+      "epoch": 0.05917159763313609,
+      "grad_norm": 1264.0,
+      "learning_rate": 8e-05,
+      "loss": 3.6953,
+      "step": 50
+    },
+    {
+      "epoch": 0.07100591715976332,
+      "grad_norm": 628.0,
+      "learning_rate": 9.6e-05,
+      "loss": 4.0786,
+      "step": 60
+    },
+    {
+      "epoch": 0.07100591715976332,
+      "eval_loss": 4.402740955352783,
+      "eval_runtime": 2.7341,
+      "eval_samples_per_second": 549.363,
+      "eval_steps_per_second": 34.381,
+      "step": 60
+    },
+    {
+      "epoch": 0.08284023668639054,
+      "grad_norm": 177.0,
+      "learning_rate": 0.00011200000000000001,
+      "loss": 5.1332,
+      "step": 70
+    },
+    {
+      "epoch": 0.09467455621301775,
+      "grad_norm": 544.0,
+      "learning_rate": 0.00012800000000000002,
+      "loss": 6.3443,
+      "step": 80
+    },
+    {
+      "epoch": 0.09467455621301775,
+      "eval_loss": 6.491352558135986,
+      "eval_runtime": 2.8019,
+      "eval_samples_per_second": 536.068,
+      "eval_steps_per_second": 33.549,
+      "step": 80
     }
   ],
   "logging_steps": 10,
@@ -78,7 +122,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 978655140380672.0,
+  "total_flos": 1951231694077952.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a52d3e140a9c869be837f2f5951de9c85ece2feebda3050bdbdf01146f07bb76
+oid sha256:ca8d159720c49ca51f8eb0994bc3f3c8474920a7e87f735362a6f81f5852cd00
 size 6712