Training in progress, step 870000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33c2dd3be5413f957dd0bc28a15d74ed06d6494592da1e0b0b7a9b5cff98543f
+oid sha256:7de9e7a475185d5a4f5233f2eaa1e382e39bf61b0b26422c710d12b1c428f053
 size 893441093

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a71f43fa4af460f6d355ec42e55c1a209c0d00e00e1e71a83db48fda6386bd08
+oid sha256:2cc5f078f248ee95608611561bbd9aea19a49de30cb9f351661140392a113dcb
 size 449450757

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e95df6a4d037778eea05d14b6a856440647a0d0d1cd96b14fe0089db3d2ca05
+oid sha256:dc1e6c47e318d84077f6a967794dd3042b980af9f2017841afbd1886d7db9904
 size 14583

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e461a2edfce20979aaf8643fc972588013ea8710a13005a233ed1e93cff795c
+oid sha256:4623ab6fbb26e814bfa3dd96c774e4b841513bb02553b1e19ff1a3408dd2f2ba
 size 14583

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ce93d230c2b3e0029a85fd7329dfec40cd7b3ce89657776854f91684f3563c3
+oid sha256:b84195dd425f6794c5806a9bed14c1dd56437e46af995a7b88fe65b75813426e
 size 14583

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e389a444854e3a8498410c2bcb75d082ab0efa10fdcbb6bf4f0273b2bb86e5d
+oid sha256:a330644903d9cebc0a0cef1ede19ebdfcc46633ad2affcbf69e9f23412d356cb
 size 14583

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5700265db9033170469a10a97e864c396caa87c59262a13775cece6d18e13d0d
+oid sha256:d23d54ddb4a3e42a55be419de46e8b2afb37f587b9bc4ebb416244cb1aa1460d
 size 14583

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0f1d070f7247d43e02284bd789b296fa89aaa5d91db9a24f1226ebc2a6cb000
+oid sha256:50c90440bc56cdec79071a507653e9cc50024a2dbba647fc3d934431503f32da
 size 14583

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b4a68e81a6718c76544b602cd99c9a2dc4ab2f4f768d0dfcb99f521ee1fd60e
+oid sha256:f41c8eaa88d8a5dc08e3c2e3def98b7a8b86cad84a79d3f83ed3a1a7c681beb0
 size 14583

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a84068892fd087eddda1aa0aa2f97caf64ae34a34d55297ff6867be4553c6f26
+oid sha256:b1faf83b262a97abbbb6024851cdc5f7c1c92261d8aa4e9260f21590a330cc4e
 size 14583

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31e18eaa468ae4a1684f551cb018df5d6a9cb8eadcd4fdd17b09a3c12ad301d8
+oid sha256:843b249180999e01b18cb497ce97e55f21bbe186ae977c32256fbedc40db0e39
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.2590859447867921,
-  "global_step": 860000,
+  "epoch": 1.2790156328473148,
+  "global_step": 870000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -10326,11 +10326,131 @@
       "learning_rate": 1.7368946912546556e-05,
       "loss": 0.2878,
       "step": 860000
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 1.7317340758783407e-05,
+      "loss": 0.2875,
+      "step": 860500
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 1.726590597701708e-05,
+      "loss": 0.2874,
+      "step": 861000
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 1.7214642707868325e-05,
+      "loss": 0.2863,
+      "step": 861500
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 1.7163551091488952e-05,
+      "loss": 0.2869,
+      "step": 862000
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 1.711263126756148e-05,
+      "loss": 0.2867,
+      "step": 862500
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 1.7061883375298788e-05,
+      "loss": 0.2874,
+      "step": 863000
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 1.7011307553443647e-05,
+      "loss": 0.286,
+      "step": 863500
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 1.6960903940268456e-05,
+      "loss": 0.2873,
+      "step": 864000
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 1.6910672673574746e-05,
+      "loss": 0.2867,
+      "step": 864500
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 1.6860613890692876e-05,
+      "loss": 0.2872,
+      "step": 865000
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 1.6810727728481673e-05,
+      "loss": 0.2864,
+      "step": 865500
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 1.6761014323327962e-05,
+      "loss": 0.2866,
+      "step": 866000
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 1.6711473811146333e-05,
+      "loss": 0.2867,
+      "step": 866500
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 1.6662106327378645e-05,
+      "loss": 0.2869,
+      "step": 867000
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 1.6612912006993688e-05,
+      "loss": 0.2867,
+      "step": 867500
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 1.6563890984486884e-05,
+      "loss": 0.2866,
+      "step": 868000
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 1.6515043393879825e-05,
+      "loss": 0.287,
+      "step": 868500
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 1.6466369368719955e-05,
+      "loss": 0.2868,
+      "step": 869000
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 1.641786904208022e-05,
+      "loss": 0.2865,
+      "step": 869500
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 1.6369542546558626e-05,
+      "loss": 0.2864,
+      "step": 870000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 2,
-  "total_flos": 5.8141983412238066e+22,
+  "total_flos": 5.881811674297794e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a71f43fa4af460f6d355ec42e55c1a209c0d00e00e1e71a83db48fda6386bd08
+oid sha256:2cc5f078f248ee95608611561bbd9aea19a49de30cb9f351661140392a113dcb
 size 449450757