Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0f38c4baa92fd93d3aac0b8c52de1ccce7b49b2b0b8c5332230ed1b296633f7
+oid sha256:9dada59e55e95e2400430a3fa779d1a320c80de9757317978ce37068cb0e4629
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5da069cd71de9adf82752d381338b2c8ff2b77463ee441d24ece7ab713395b6
+oid sha256:661d11eb8c7b88525f8954ec05ac9836f2d13050ee54ba9ea88a81d9ce6ca539
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10022306343bd94ea9f520380d484d08b66b199ed721f24854ec09f2e0e49f9e
+oid sha256:a6c51394d4d9a5546712570810c55b6767a5de4a969fd8bb1026d4ad8b7aa26b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c931ece4da598a541d357f6c98f67481603252e193960022d37ddd49c584b1f
+oid sha256:a89ffc445067fef9d6d02bb3ff9e61d5e3209e6fa67c7259b3b364b90dbaa2cd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.10351966873706005,
+  "epoch": 0.2070393374741201,
   "eval_steps": 9,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -206,6 +206,205 @@
       "learning_rate": 9.330127018922194e-05,
       "loss": 2.0118,
       "step": 25
+    },
+    {
+      "epoch": 0.10766045548654245,
+      "grad_norm": 1.2384679317474365,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 1.8618,
+      "step": 26
+    },
+    {
+      "epoch": 0.11180124223602485,
+      "grad_norm": 1.2058842182159424,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 1.8744,
+      "step": 27
+    },
+    {
+      "epoch": 0.11180124223602485,
+      "eval_loss": 1.000207543373108,
+      "eval_runtime": 86.613,
+      "eval_samples_per_second": 2.355,
+      "eval_steps_per_second": 0.3,
+      "step": 27
+    },
+    {
+      "epoch": 0.11594202898550725,
+      "grad_norm": 1.3206522464752197,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 2.4724,
+      "step": 28
+    },
+    {
+      "epoch": 0.12008281573498965,
+      "grad_norm": 1.1769299507141113,
+      "learning_rate": 8.940053768033609e-05,
+      "loss": 2.2312,
+      "step": 29
+    },
+    {
+      "epoch": 0.12422360248447205,
+      "grad_norm": 1.1039841175079346,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 1.8363,
+      "step": 30
+    },
+    {
+      "epoch": 0.12836438923395446,
+      "grad_norm": 1.1677961349487305,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 2.0295,
+      "step": 31
+    },
+    {
+      "epoch": 0.13250517598343686,
+      "grad_norm": 1.136795163154602,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 1.7927,
+      "step": 32
+    },
+    {
+      "epoch": 0.13664596273291926,
+      "grad_norm": 1.1699427366256714,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 2.1008,
+      "step": 33
+    },
+    {
+      "epoch": 0.14078674948240166,
+      "grad_norm": 1.0956039428710938,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 1.8778,
+      "step": 34
+    },
+    {
+      "epoch": 0.14492753623188406,
+      "grad_norm": 1.106882929801941,
+      "learning_rate": 8.213938048432697e-05,
+      "loss": 1.8638,
+      "step": 35
+    },
+    {
+      "epoch": 0.14906832298136646,
+      "grad_norm": 1.176102638244629,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 2.0063,
+      "step": 36
+    },
+    {
+      "epoch": 0.14906832298136646,
+      "eval_loss": 0.9627537727355957,
+      "eval_runtime": 86.6445,
+      "eval_samples_per_second": 2.354,
+      "eval_steps_per_second": 0.3,
+      "step": 36
+    },
+    {
+      "epoch": 0.15320910973084886,
+      "grad_norm": 1.2707808017730713,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 2.0563,
+      "step": 37
+    },
+    {
+      "epoch": 0.15734989648033126,
+      "grad_norm": 1.1810678243637085,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 1.7766,
+      "step": 38
+    },
+    {
+      "epoch": 0.16149068322981366,
+      "grad_norm": 1.2528388500213623,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 2.2023,
+      "step": 39
+    },
+    {
+      "epoch": 0.16563146997929606,
+      "grad_norm": 1.1106541156768799,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 1.9607,
+      "step": 40
+    },
+    {
+      "epoch": 0.16977225672877846,
+      "grad_norm": 1.3797121047973633,
+      "learning_rate": 7.347357813929454e-05,
+      "loss": 2.2966,
+      "step": 41
+    },
+    {
+      "epoch": 0.17391304347826086,
+      "grad_norm": 1.0759304761886597,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 1.9743,
+      "step": 42
+    },
+    {
+      "epoch": 0.17805383022774326,
+      "grad_norm": 1.485608696937561,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 2.1251,
+      "step": 43
+    },
+    {
+      "epoch": 0.18219461697722567,
+      "grad_norm": 1.1569021940231323,
+      "learning_rate": 6.873032967079561e-05,
+      "loss": 1.9108,
+      "step": 44
+    },
+    {
+      "epoch": 0.18633540372670807,
+      "grad_norm": 1.4364919662475586,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 2.561,
+      "step": 45
+    },
+    {
+      "epoch": 0.18633540372670807,
+      "eval_loss": 0.9237259030342102,
+      "eval_runtime": 86.6431,
+      "eval_samples_per_second": 2.354,
+      "eval_steps_per_second": 0.3,
+      "step": 45
+    },
+    {
+      "epoch": 0.19047619047619047,
+      "grad_norm": 1.126060128211975,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 1.8225,
+      "step": 46
+    },
+    {
+      "epoch": 0.19461697722567287,
+      "grad_norm": 1.137122392654419,
+      "learning_rate": 6.378186779084995e-05,
+      "loss": 1.8008,
+      "step": 47
+    },
+    {
+      "epoch": 0.19875776397515527,
+      "grad_norm": 1.1307929754257202,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 1.8732,
+      "step": 48
+    },
+    {
+      "epoch": 0.2028985507246377,
+      "grad_norm": 1.3419166803359985,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 1.782,
+      "step": 49
+    },
+    {
+      "epoch": 0.2070393374741201,
+      "grad_norm": 1.3455865383148193,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 1.4769,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -225,7 +424,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.840003565355008e+16,
+  "total_flos": 1.1489572231839744e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null