Training in progress, step 900, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbb88cd2ad49a28dfd1cc411e4818df1e3111793a50f870549a2cf9e7bc00e62
+oid sha256:bd3d3749c1bd6d89c5172acc406cbf998cb265de2f8a059883bd34374666967b
 size 18516456

last-checkpoint/global_step900/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:964dceb2d1c22487dfbebd0d53b2f63cedabf0e75e9fdd5e0cb695b97b0db0dc
+size 27700976

last-checkpoint/global_step900/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4d4887bea23f6c293fde5bd52a7c93321a682d20078bd1062171d640d30fc58
+size 27700976

last-checkpoint/global_step900/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8685412a783a9bc817af6781ffae7ede79677eed452dc9dcec24a05927fc12bd
+size 27700976

last-checkpoint/global_step900/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e123ddc7d82c0c4a1d3c8efe3135d938104bd399f98cf72628c9c03187f96d03
+size 27700976

last-checkpoint/global_step900/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6784c2006ba47df1330cad40d3f78cd8df0c9123cc6f8133a332365da69d320
+size 411571

last-checkpoint/global_step900/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:593f93ba7969fb31276e8b0d92b9626d76b4d0011b4d4d9c5984437d53477ee1
+size 411507

last-checkpoint/global_step900/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d1ad7550f305c82bd88f505357dac1dd21c2a343a42c6fd0af8b64e3340d393
+size 411507

last-checkpoint/global_step900/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ae307050315e3d6f9b17d0fa78301afb1254ce58b4687170fb920516e319b71
+size 411507

last-checkpoint/latest

@@ -1 +1 @@
-global_step850
+global_step900

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36c9044354f826de248840acaaec171f816609c147a664089731a0570deef948
+oid sha256:b8f22ced19e790cc864cefe3b7c711d9ae631c44f95d42fb4829688cc3de0153
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54f4c4013326db4e7267b656aaf72b86570f8aeee91ad39242a416cf8b963191
+oid sha256:3e0407513eba77d34cbf3adf0e59a58bd80716f4f00f414854253637e82be43d
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43e910793831957d8685c316138c33eef8867edf60052477dc9ad6ec0c6da901
+oid sha256:6060636c023258ce9b965e244b8a58b4c99d5784dde4405b39737550ef50cd4f
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7cfd0d71ef5a6c58d9f1d46851f4b1e699ca8a50ab3223cfb39668895cffeef2
+oid sha256:c24ccdfdcde39cb2265c82c50c36ffdfcc670f757aba4bcf4bb0fdc6d1373c4c
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e24eaa8963cd872c048c2c655789d678b8c3fcd1c77ca0d663feee5857d2e34
+oid sha256:feb4015894f59edc29c71bc4938b5d4ab98daad34a38a3d387b308b3b1d4b280
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.8779178261756897,
   "best_model_checkpoint": "saves/CADICA_qwenvl_stenosis_classily_scale4_frozenVision/lora/sft/checkpoint-850",
-  "epoch": 0.43780582024208087,
+  "epoch": 0.4635591037857327,
   "eval_steps": 50,
-  "global_step": 850,
+  "global_step": 900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1520,11 +1520,100 @@
       "eval_steps_per_second": 0.928,
       "num_input_tokens_seen": 9941896,
       "step": 850
+    },
+    {
+      "epoch": 0.44038114859644606,
+      "grad_norm": 0.8207188524660312,
+      "learning_rate": 8.930720915538487e-05,
+      "loss": 0.8516,
+      "num_input_tokens_seen": 10000336,
+      "step": 855
+    },
+    {
+      "epoch": 0.44295647695081125,
+      "grad_norm": 1.5881804699369033,
+      "learning_rate": 8.915646321965614e-05,
+      "loss": 0.9206,
+      "num_input_tokens_seen": 10058816,
+      "step": 860
+    },
+    {
+      "epoch": 0.4455318053051764,
+      "grad_norm": 0.3364043503653687,
+      "learning_rate": 8.900479122779712e-05,
+      "loss": 0.9028,
+      "num_input_tokens_seen": 10117320,
+      "step": 865
+    },
+    {
+      "epoch": 0.4481071336595416,
+      "grad_norm": 0.2888069815557639,
+      "learning_rate": 8.885219676687277e-05,
+      "loss": 0.8991,
+      "num_input_tokens_seen": 10175824,
+      "step": 870
+    },
+    {
+      "epoch": 0.45068246201390677,
+      "grad_norm": 0.26081919755231314,
+      "learning_rate": 8.869868344576459e-05,
+      "loss": 0.8934,
+      "num_input_tokens_seen": 10234288,
+      "step": 875
+    },
+    {
+      "epoch": 0.45325779036827196,
+      "grad_norm": 0.1672074260476841,
+      "learning_rate": 8.854425489508532e-05,
+      "loss": 0.8908,
+      "num_input_tokens_seen": 10292736,
+      "step": 880
+    },
+    {
+      "epoch": 0.45583311872263715,
+      "grad_norm": 0.3141498425127344,
+      "learning_rate": 8.838891476709288e-05,
+      "loss": 0.8988,
+      "num_input_tokens_seen": 10351224,
+      "step": 885
+    },
+    {
+      "epoch": 0.4584084470770023,
+      "grad_norm": 0.28442383194638554,
+      "learning_rate": 8.823266673560426e-05,
+      "loss": 0.8965,
+      "num_input_tokens_seen": 10409736,
+      "step": 890
+    },
+    {
+      "epoch": 0.4609837754313675,
+      "grad_norm": 0.24793143025843287,
+      "learning_rate": 8.807551449590846e-05,
+      "loss": 0.8989,
+      "num_input_tokens_seen": 10468240,
+      "step": 895
+    },
+    {
+      "epoch": 0.4635591037857327,
+      "grad_norm": 0.18173090045802157,
+      "learning_rate": 8.791746176467907e-05,
+      "loss": 0.8961,
+      "num_input_tokens_seen": 10526712,
+      "step": 900
+    },
+    {
+      "epoch": 0.4635591037857327,
+      "eval_loss": 0.891426146030426,
+      "eval_runtime": 16.0357,
+      "eval_samples_per_second": 3.742,
+      "eval_steps_per_second": 0.935,
+      "num_input_tokens_seen": 10526712,
+      "step": 900
     }
   ],
   "logging_steps": 5,
   "max_steps": 3400,
-  "num_input_tokens_seen": 9941896,
+  "num_input_tokens_seen": 10526712,
   "num_train_epochs": 2,
   "save_steps": 50,
   "stateful_callbacks": {
@@ -1539,7 +1628,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 558240938328064.0,
+  "total_flos": 591081256517632.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null