Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1855b04f9bebe3b08e07de19993d6cfedd0a18805c06a4488320ed80a47c45f3
+oid sha256:2d2c7f8a4ed21ccfa9124972bb6565f42e77a90dc33b333ccf177f72c3db3dd3
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:276828d449acab10469ccc2d06c7ea6c78e7f722ea69d8f191de5b96f38a89fd
+oid sha256:6088dc64cbe0ac01faadfae0eaed9a2310d161874529eebd4f42e66e32db7ca2
 size 335922386

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9abfa9a8d14e1e228c48dd1ac4e886006b4dce52560af935390a530a1e0d643d
+oid sha256:146eb5506064fb4ca3bcd461d553541c18c3ad661a9fffff0c43399202ffb137
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:640c01bc8334a74f73b25965a05b787223e930210338d853eb784ba9cf2a8f5b
+oid sha256:5638d3c6abe10668193456baecbe88e2a7a80e3ab2e23c2f753dd99e2ddc2467
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f95cde59a802153564e2e037db5cc1a1ad8ffe99e7a108ba969ddce37184677
+oid sha256:9ca6a10bf1a8dd7587f60576e0017d28e3d7190095a2b23aaa57aad2ecfcd7e5
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38240cce99ecd790e508448166110c73b8c0acdcd25add62419b93a353df8ccd
+oid sha256:9bca20e85bb4c9fe024050b4ce0513f921870d198211baeb02b2ecb4aeaa4c0f
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a89ffc445067fef9d6d02bb3ff9e61d5e3209e6fa67c7259b3b364b90dbaa2cd
+oid sha256:f23e2214bcafb439ebc7528dcc283ef6218d509a276c0baff0743503ecbe3d92
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0546448087431694,
+  "epoch": 0.08196721311475409,
   "eval_steps": 9,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -405,6 +405,205 @@
       "learning_rate": 5.868240888334653e-05,
       "loss": 5.0935,
       "step": 50
+    },
+    {
+      "epoch": 0.05573770491803279,
+      "grad_norm": 2.6530776023864746,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 4.9609,
+      "step": 51
+    },
+    {
+      "epoch": 0.05683060109289618,
+      "grad_norm": 1.504117727279663,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 4.8891,
+      "step": 52
+    },
+    {
+      "epoch": 0.05792349726775956,
+      "grad_norm": 1.8544734716415405,
+      "learning_rate": 5.348782368720626e-05,
+      "loss": 4.9346,
+      "step": 53
+    },
+    {
+      "epoch": 0.05901639344262295,
+      "grad_norm": 1.908761739730835,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 4.9979,
+      "step": 54
+    },
+    {
+      "epoch": 0.05901639344262295,
+      "eval_loss": 4.928157329559326,
+      "eval_runtime": 55.6535,
+      "eval_samples_per_second": 55.36,
+      "eval_steps_per_second": 1.743,
+      "step": 54
+    },
+    {
+      "epoch": 0.060109289617486336,
+      "grad_norm": 0.9097221493721008,
+      "learning_rate": 5e-05,
+      "loss": 4.9558,
+      "step": 55
+    },
+    {
+      "epoch": 0.06120218579234973,
+      "grad_norm": 1.899079442024231,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 4.9715,
+      "step": 56
+    },
+    {
+      "epoch": 0.06229508196721312,
+      "grad_norm": 1.7221193313598633,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 4.9064,
+      "step": 57
+    },
+    {
+      "epoch": 0.0633879781420765,
+      "grad_norm": 0.7375671863555908,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 4.8998,
+      "step": 58
+    },
+    {
+      "epoch": 0.06448087431693988,
+      "grad_norm": 1.5496197938919067,
+      "learning_rate": 4.3041344951996746e-05,
+      "loss": 4.9465,
+      "step": 59
+    },
+    {
+      "epoch": 0.06557377049180328,
+      "grad_norm": 1.029213309288025,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 4.9669,
+      "step": 60
+    },
+    {
+      "epoch": 0.06666666666666667,
+      "grad_norm": 0.6538008451461792,
+      "learning_rate": 3.960441545911204e-05,
+      "loss": 4.8936,
+      "step": 61
+    },
+    {
+      "epoch": 0.06775956284153005,
+      "grad_norm": 1.0834981203079224,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 4.9531,
+      "step": 62
+    },
+    {
+      "epoch": 0.06885245901639345,
+      "grad_norm": 0.691550612449646,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 4.9323,
+      "step": 63
+    },
+    {
+      "epoch": 0.06885245901639345,
+      "eval_loss": 4.916704177856445,
+      "eval_runtime": 55.705,
+      "eval_samples_per_second": 55.309,
+      "eval_steps_per_second": 1.741,
+      "step": 63
+    },
+    {
+      "epoch": 0.06994535519125683,
+      "grad_norm": 0.45348408818244934,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 4.8709,
+      "step": 64
+    },
+    {
+      "epoch": 0.07103825136612021,
+      "grad_norm": 1.04542875289917,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 4.952,
+      "step": 65
+    },
+    {
+      "epoch": 0.07213114754098361,
+      "grad_norm": 0.697375476360321,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 4.9087,
+      "step": 66
+    },
+    {
+      "epoch": 0.073224043715847,
+      "grad_norm": 0.8204128742218018,
+      "learning_rate": 2.9663167846209998e-05,
+      "loss": 4.9664,
+      "step": 67
+    },
+    {
+      "epoch": 0.07431693989071038,
+      "grad_norm": 1.083094835281372,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 4.9942,
+      "step": 68
+    },
+    {
+      "epoch": 0.07540983606557378,
+      "grad_norm": 0.5777742862701416,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 4.9119,
+      "step": 69
+    },
+    {
+      "epoch": 0.07650273224043716,
+      "grad_norm": 0.9902992248535156,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 4.8564,
+      "step": 70
+    },
+    {
+      "epoch": 0.07759562841530054,
+      "grad_norm": 0.69707190990448,
+      "learning_rate": 2.350403678833976e-05,
+      "loss": 4.8472,
+      "step": 71
+    },
+    {
+      "epoch": 0.07868852459016394,
+      "grad_norm": 0.5401630997657776,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 4.946,
+      "step": 72
+    },
+    {
+      "epoch": 0.07868852459016394,
+      "eval_loss": 4.9106550216674805,
+      "eval_runtime": 55.7387,
+      "eval_samples_per_second": 55.276,
+      "eval_steps_per_second": 1.74,
+      "step": 72
+    },
+    {
+      "epoch": 0.07978142076502732,
+      "grad_norm": 0.41800597310066223,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 4.9306,
+      "step": 73
+    },
+    {
+      "epoch": 0.08087431693989071,
+      "grad_norm": 0.9597459435462952,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 4.9114,
+      "step": 74
+    },
+    {
+      "epoch": 0.08196721311475409,
+      "grad_norm": 0.4304816722869873,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 4.8847,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -424,7 +623,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.6877935935881216e+17,
+  "total_flos": 2.496450742064251e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null